SlideShare a Scribd company logo
1 of 49
© 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Cómo crear aplicaciones inteligentes con
inteligencia artificial en AWS
Edzon Sánchez
Machine Learning Specialist
© 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved.
VISIÓN SPEECH TEXTO BÚSQUEDAS CHATBOTS PERSONALIZACIÓN PRONÓSTICOS FRAUDES DESARROLLO
CENTROS DE
CONTACTO
Stackde servicios deAI/MachineLearning
SERVICIOS DE INTELIGENCIA ARTIFICIAL
Amazon
Rekognition
Amazon
Polly
Amazon
Transcribe
+Medical
Amazon
Comprehend
+Medical
Amazon
Translate
Amazon
Lex
Amazon
Personalize
Amazon
Forecast
Amazon
Fraud Detector
Amazon
CodeGuru
Amazon
Textract
Amazon
Kendra
Contact Lens
For Amazon
Connect
¡Nuevo! ¡Nuevo! ¡Nuevo! ¡Nuevo!
© 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved.
VISIÓN SPEECH TEXTO BÚSQUEDAS CHATBOTS PERSONALIZACIÓN PRONÓSTICOS FRAUDES DESARROLLO
CENTROS DE
CONTACTO
Stackde servicios deAI/MachineLearning
SERVICIOS DE INTELIGENCIA
ARTIFICIAL
Amazon
Rekognition
Amazon
Polly
Amazon
Transcribe
+Medical
Amazon
Comprehend
+Medical
Amazon
Translate
Amazon
Lex
Amazon
Personalize
Amazon
Forecast
Amazon
Fraud Detector
Amazon
CodeGuru
Amazon
Textract
Amazon
Kendra
Contact Lens
For Amazon
Connect
¡Nuevo!
¡Nuevo! ¡Nuevo! ¡Nuevo! ¡Nuevo!
Ground
Truth
Augmented
AI
ML
Marketplace
Neo
Algoritmos
incluidos
Notebooks Experiments
Entrenamiento y
optimización de
modelos
Debugger Autopilot
Hosting de
modelos
Model Monitor
SERVICIOS DE MACHINE LEARNING
SageMaker Studio IDE ¡Nuevo!
¡Nuevo! ¡Nuevo! ¡Nuevo! ¡Nuevo! ¡Nuevo!
Amazon SageMaker
© 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved.
VISIÓN SPEECH TEXTO BÚSQUEDAS CHATBOTS PERSONALIZACIÓN PRONÓSTICOS FRAUDES DESARROLLO
CENTROS DE
CONTACTO
Stackde servicios deAI/MachineLearning
SERVICIOS DE INTELIGENCIA ARTIFICIAL
Amazon
Rekognition
Amazon
Polly
Amazon
Transcribe
+Medical
Amazon
Comprehend
+Medical
Amazon
Translate
Amazon
Lex
Amazon
Personalize
Amazon
Forecast
Amazon
Fraud Detector
Amazon
CodeGuru
Amazon
Textract
Amazon
Kendra
Contact Lens
For Amazon
Connect
¡Nuevo!
¡Nuevo! ¡Nuevo! ¡Nuevo! ¡Nuevo!
Ground
Truth
Augmented
AI
ML
Marketplace
Neo
Algoritmos
incluidos
Notebooks Experiments
Entrenamiento y
optimización de
modelos
Debugger Autopilot
Hosting de
modelos
Model Monitor
Deep Learning
AMIs & Containers
GPUs &
CPUs
Elastic
Inference
Inferentia FPGA
SERVICIOS DE MACHINE LEARNING
ML FRAMEWORKS E INFRASTRUCTURA
SageMaker Studio IDE ¡Nuevo!
¡Nuevo! ¡Nuevo! ¡Nuevo! ¡Nuevo! ¡Nuevo!
Amazon SageMaker
© 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved.
© 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Amazon Rekognition
Reconocimiento de objetos,
escenas y actividades
Reconocimiento facial Análisis facial Rastreo de personas
Detección de contenido no
apropiado
Reconocimiento de
celebridades
Texto en imágenes
A n á l i s i s d e i m á g e n e s y v i d e o b a s a d o e n D e e p l e a r n i n g
© 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved.
import boto3
region = boto3.Session().region_name
rekognition=boto3.client(service_name='rekognition', region_name=region)
bucket='bucket'
photo='photo.jpg'
response = rekognition.detect_labels(
Image={'S3Object':{'Bucket':bucket,'Name':photo}},
MaxLabels=10,
MinConfidence=0.8)
print('Detected labels for ' + photo)
for label in response['Labels']:
print ("Label: " + label['Name'])
print ("Confidence: " + str(label['Confidence']))
print ("Instances:")
for instance in label['Instances']:
print (" Bounding box")
print (" Top: " + str(instance['BoundingBox']['Top']))
print (" Left: " + str(instance['BoundingBox']['Left']))
print (" Width: " + str(instance['BoundingBox']['Width']))
print (" Height: " + str(instance['BoundingBox']['Height']))
print (" Confidence: " + str(instance['Confidence']))
Amazon Rekognition -Python
© 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved.
import boto3
region = boto3.Session().region_name
rekognition=boto3.client(service_name='rekognition', region_name=region)
bucket='bucket'
photo='photo.jpg'
response = rekognition.detect_labels(
Image={'S3Object':{'Bucket':bucket,'Name':photo}},
MaxLabels=10,
MinConfidence=0.8)
print('Detected labels for ' + photo)
for label in response['Labels']:
print ("Label: " + label['Name'])
print ("Confidence: " + str(label['Confidence']))
print ("Instances:")
for instance in label['Instances']:
print (" Bounding box")
print (" Top: " + str(instance['BoundingBox']['Top']))
print (" Left: " + str(instance['BoundingBox']['Left']))
print (" Width: " + str(instance['BoundingBox']['Width']))
print (" Height: " + str(instance['BoundingBox']['Height']))
print (" Confidence: " + str(instance['Confidence']))
Amazon Rekognition -Python
© 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved.
import boto3
region = boto3.Session().region_name
rekognition=boto3.client(service_name='rekognition', region_name=region)
bucket='bucket'
photo='photo.jpg'
response = rekognition.detect_labels(
Image={'S3Object':{'Bucket':bucket,'Name':photo}},
MaxLabels=10,
MinConfidence=0.8)
print('Detected labels for ' + photo)
for label in response['Labels']:
print ("Label: " + label['Name'])
print ("Confidence: " + str(label['Confidence']))
print ("Instances:")
for instance in label['Instances']:
print (" Bounding box")
print (" Top: " + str(instance['BoundingBox']['Top']))
print (" Left: " + str(instance['BoundingBox']['Left']))
print (" Width: " + str(instance['BoundingBox']['Width']))
print (" Height: " + str(instance['BoundingBox']['Height']))
print (" Confidence: " + str(instance['Confidence']))
Amazon Rekognition -Python
© 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved.
import boto3
region = boto3.Session().region_name
rekognition=boto3.client(service_name='rekognition', region_name=region)
bucket='bucket'
photo='photo.jpg'
response = rekognition.detect_labels(
Image={'S3Object':{'Bucket':bucket,'Name':photo}},
MaxLabels=10,
MinConfidence=0.8)
print('Detected labels for ' + photo)
for label in response['Labels']:
print ("Label: " + label['Name'])
print ("Confidence: " + str(label['Confidence']))
print ("Instances:")
for instance in label['Instances']:
print (" Bounding box")
print (" Top: " + str(instance['BoundingBox']['Top']))
print (" Left: " + str(instance['BoundingBox']['Left']))
print (" Width: " + str(instance['BoundingBox']['Width']))
print (" Height: " + str(instance['BoundingBox']['Height']))
print (" Confidence: " + str(instance['Confidence']))
Amazon Rekognition -Python
© 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved.
import boto3
region = boto3.Session().region_name
rekognition=boto3.client(service_name='rekognition', region_name=region)
bucket='bucket'
photo='photo.jpg'
response = rekognition.detect_labels(
Image={'S3Object':{'Bucket':bucket,'Name':photo}},
MaxLabels=10,
MinConfidence=0.8)
print('Detected labels for ' + photo)
for label in response['Labels']:
print ("Label: " + label['Name'])
print ("Confidence: " + str(label['Confidence']))
print ("Instances:")
for instance in label['Instances']:
print (" Bounding box")
print (" Top: " + str(instance['BoundingBox']['Top']))
print (" Left: " + str(instance['BoundingBox']['Left']))
print (" Width: " + str(instance['BoundingBox']['Width']))
print (" Height: " + str(instance['BoundingBox']['Height']))
print (" Confidence: " + str(instance['Confidence']))
Amazon Rekognition -Python
© 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Amazon Rekognition -Pythonimport boto3
region = boto3.Session().region_name
rekognition=boto3.client(service_name='rekognition', region_name=region)
bucket='bucket'
photo='photo.jpg'
response = rekognition.detect_labels(
Image={'S3Object':{'Bucket':bucket,'Name':photo}},
MaxLabels=10,
MinConfidence=0.8)
print('Detected labels for ' + photo)
for label in response['Labels']:
print ("Label: " + label['Name'])
print ("Confidence: " + str(label['Confidence']))
print ("Instances:")
for instance in label['Instances']:
print (" Bounding box")
print (" Top: " + str(instance['BoundingBox']['Top']))
print (" Left: " + str(instance['BoundingBox']['Left']))
print (" Width: " + str(instance['BoundingBox']['Width']))
print (" Height: " + str(instance['BoundingBox']['Height']))
print (" Confidence: " + str(instance['Confidence']))
© 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved.
AmazonTranscribe
C o n v e r s i ó n a u t o m á t i c a d e v o z e n t e x t o p r e c i s o y g r a m a t i c a l m e n t e c o r r e c t o
Soporte para
audio telefónico
Time stamps a
nivel de palabra
Puntuación y formato
automático
Identificación de
interlocutor
Vocabulario
personalizado
Multiples
idiomas
© 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved.
AmazonTranslate
Tr a d u c c i ó n c o n f l u i d e z n a t u r a l
Reconocimiento
automático de idioma
Análisis en batchTraducción en
tiempo-real
© 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Amazon Polly
C o n v i e r t e t e x t o e n v o z q u e p a r e c e n a t u r a l , u t i l i z a n d o d e e p l e a r n i n g
Amplia selección de
voces e idiomas
Voz sincronizable Fino control granular Reproducción
ilimitada
© 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved.
AmazonComprehend
D e s c u b r e i n f o r m a c i ó n r e l e v a n t e y r e l a c i o n e s e n e l t e x t o
Amazon
Comprehend
Entidades
Frases clave
Idioma
Sentimiento
Modelado de tópico
© 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved.
AmazonComprehend -Python
import boto3
import json
region = boto3.Session().region_name
comprehend = boto3.client(service_name='comprehend', region_name=region)
text = 'Amazon.com, Inc localizado en Seattle, WA fue fundado 
el 5 de Julio de 1994 por Jeff Bezos'
lang = comprehend.detect_dominant_language(Text=text)
response = comprehend.detect_entities(Text=text, LanguageCode=lang)
print(json.dumps(response, sort_keys=True, indent=4))
response = comprehend.detect_key_phrases(Text=text, LanguageCode=lang)
print(json.dumps(response, sort_keys=True, indent=4))
response = comprehend.detect_sentiment(Text=text, LanguageCode=lang)
print(json.dumps(response, sort_keys=True, indent=4))
© 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved.
AmazonComprehend -Python
import boto3
import json
region = boto3.Session().region_name
comprehend = boto3.client(service_name='comprehend', region_name=region)
text = 'Amazon.com, Inc localizado en Seattle, WA fue fundado 
el 5 de Julio de 1994 por Jeff Bezos'
lang = comprehend.detect_dominant_language(Text=text)
response = comprehend.detect_entities(Text=text, LanguageCode=lang)
print(json.dumps(response, sort_keys=True, indent=4))
response = comprehend.detect_key_phrases(Text=text, LanguageCode=lang)
print(json.dumps(response, sort_keys=True, indent=4))
response = comprehend.detect_sentiment(Text=text, LanguageCode=lang)
print(json.dumps(response, sort_keys=True, indent=4))
© 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved.
AmazonComprehend -Python
import boto3
import json
region = boto3.Session().region_name
comprehend = boto3.client(service_name='comprehend', region_name=region)
text = 'Amazon.com, Inc localizado en Seattle, WA fue fundado 
el 5 de Julio de 1994 por Jeff Bezos'
lang = comprehend.detect_dominant_language(Text=text)
response = comprehend.detect_entities(Text=text, LanguageCode=lang)
print(json.dumps(response, sort_keys=True, indent=4))
response = comprehend.detect_key_phrases(Text=text, LanguageCode=lang)
print(json.dumps(response, sort_keys=True, indent=4))
response = comprehend.detect_sentiment(Text=text, LanguageCode=lang)
print(json.dumps(response, sort_keys=True, indent=4))
© 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved.
AmazonComprehend -Python
import boto3
import json
region = boto3.Session().region_name
comprehend = boto3.client(service_name='comprehend', region_name=region)
text = 'Amazon.com, Inc localizado en Seattle, WA fue fundado 
el 5 de Julio de 1994 por Jeff Bezos'
lang = comprehend.detect_dominant_language(Text=text)
response = comprehend.detect_entities(Text=text, LanguageCode=lang)
print(json.dumps(response, sort_keys=True, indent=4))
response = comprehend.detect_key_phrases(Text=text, LanguageCode=lang)
print(json.dumps(response, sort_keys=True, indent=4))
response = comprehend.detect_sentiment(Text=text, LanguageCode=lang)
print(json.dumps(response, sort_keys=True, indent=4))
© 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved.
AmazonComprehend -Python
import boto3
import json
region = boto3.Session().region_name
comprehend = boto3.client(service_name='comprehend', region_name=region)
text = 'Amazon.com, Inc localizado en Seattle, WA fue fundado 
el 5 de Julio de 1994 por Jeff Bezos'
lang = comprehend.detect_dominant_language(Text=text)
response = comprehend.detect_entities(Text=text, LanguageCode=lang)
print(json.dumps(response, sort_keys=True, indent=4))
response = comprehend.detect_key_phrases(Text=text, LanguageCode=lang)
print(json.dumps(response, sort_keys=True, indent=4))
response = comprehend.detect_sentiment(Text=text, LanguageCode=lang)
print(json.dumps(response, sort_keys=True, indent=4))
© 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved.
AmazonComprehend -Python
import boto3
import json
region = boto3.Session().region_name
comprehend = boto3.client(service_name='comprehend', region_name=region)
text = 'Amazon.com, Inc localizado en Seattle, WA fue fundado 
el 5 de Julio de 1994 por Jeff Bezos'
lang = comprehend.detect_dominant_language(Text=text)
response = comprehend.detect_entities(Text=text, LanguageCode=lang)
print(json.dumps(response, sort_keys=True, indent=4))
response = comprehend.detect_key_phrases(Text=text, LanguageCode=lang)
print(json.dumps(response, sort_keys=True, indent=4))
response = comprehend.detect_sentiment(Text=text, LanguageCode=lang)
print(json.dumps(response, sort_keys=True, indent=4))
© 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved.
AmazonComprehend -Python
import boto3
import json
region = boto3.Session().region_name
comprehend = boto3.client(service_name='comprehend', region_name=region)
text = 'Amazon.com, Inc localizado en Seattle, WA fue fundado 
el 5 de Julio de 1994 por Jeff Bezos'
lang = comprehend.detect_dominant_language(Text=text)
response = comprehend.detect_entities(Text=text, LanguageCode=lang)
print(json.dumps(response, sort_keys=True, indent=4))
response = comprehend.detect_key_phrases(Text=text, LanguageCode=lang)
print(json.dumps(response, sort_keys=True, indent=4))
response = comprehend.detect_sentiment(Text=text, LanguageCode=lang)
print(json.dumps(response, sort_keys=True, indent=4))
© 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Amazon Lex
R e c o n o c i m i e n t o a u t o m á t i c o d e v o z p a r a c o n s t r u i r a p l i c a c i o n e s c o n v e r s a c i o n a l e s
Desarrollo
integrado a la
consola AWS
Invoca
funciones
Lambda
Conversaciones
de multiples pasos
Despliegue
con un clic
Conectores
empresariales
Totalmente
administrado
© 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Elimina esfuerzo
manual
Disminuye los costos de
procesamiento de
documentos
P R I N C I PA L E S C A R A C T E R Í S T I C A S
Extrae datos de manera
rápida y exacta
Reconocimiento
Óptico de
Caracteres (OCR)
Detección de
pares llave-valor
Umbrales de confianza
ajustables
Detección de
tablas
Cuadros
delimitadores
No se require
experiencia en ML
E x t r a e t e x t o y d a t o s d e v i r t u a l m e n t e c u a l q u i e r d o c u m e n t o
AmazonTextract
© 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Fácil de utilizar, desde
la consola y el API
Funciona con cualquier
serie de tiempo histórica
P R I N C I PA L E S C A R A C T E R Í S T I C A S
Pronósticos más exactos
que integran datos
externos
Considera múltiples
series de tiempo a la
vez
Machine
Learning
automático
Visualiza los
pronósticos en la
consola e importa a
aplicaciones de negocio
Evalúa la exactitud
del modelo a través
de la consola
Calendariza los
pronósticos y el re-
entrenamiento
Integra algoritmos
existentes de
Amazon SageMaker
Amazon Forecast
M e j o r a l a e x a c t i t u d d e l a s p r e d i c c i o n e s h a s t a u n 5 0 % a u n 1 / 1 0 d e l c o s t o
© 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Tiempo-real Funciona con casi
cualquier product o
contenido
Responde a los cambios
de intención
Machine Learning
automático
Integra algoritmos existentes
de Amazon SageMaker
Entrega
recomendaciones de
alta calidad
Algoritmos de Deep
Learning
Fácil de utilizar
Amazon Personalize
M e j o r a l a e x p e r i e n c i a d e l o s c l i e n t e s c o n r e c o m e n d a c i o n e s y p e r s o n a l i z a c i ó n
P R I N C I PA L E S C A R A C T E R Í S T I C A S
© 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved.
© 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved.
AmazonSageMaker
L l e v a n d o M a c h i n e L e a r n i n g a t o d o s l o s d e s a r r o l l a d o r e s
Recolección y
preparación de los datos
de entrenamiento
Selección y
optimización del
algoritmo
Preparación y
administración de
ambientes para el
entrenamiento
Entrenamiento y
optimización del
modelo
Despliegue del
modelo en
producción
Administración y
escalamiento de
ambiente de
producción
© 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved.
AmazonSageMaker
Recolección y
preparación de los datos
de entrenamiento
Selección y
optimización del
algoritmo
Preparación y
administración de
ambientes para el
entrenamiento
Entrenamiento y
optimización del
modelo
Despliegue del
modelo en
producción
Administración y
escalamiento de
ambiente de
producción
Notebooks pre-
construidos para
problemas comunes
L l e v a n d o M a c h i n e L e a r n i n g a t o d o s l o s d e s a r r o l l a d o r e s
© 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved.
AmazonSageMaker
• K-Means Clustering
• Principal Component Analysis
• Neural Topic Modelling
• Factorization Machines
• Linear Learner (Regression)
• BlazingText
• Reinforcement learning
• XGBoost
• Topic Modeling (LDA)
• Image Classification
• Seq2Seq
• Linear Learner (Classification)
• DeepAR Forecasting
L l e v a n d o M a c h i n e L e a r n i n g a t o d o s l o s d e s a r r o l l a d o r e s
Recolección y
preparación de los datos
de entrenamiento
Selección y
optimización del
algoritmo
Notebooks pre-
construidos para
problemas comunes
Algoritmos con alto
desempeño incluidos
© 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved.
AmazonSageMaker
Entrenamiento con
un solo clic
L l e v a n d o M a c h i n e L e a r n i n g a t o d o s l o s d e s a r r o l l a d o r e s
Recolección y
preparación de los datos
de entrenamiento
Selección y
optimización del
algoritmo
Preparación y
administración de
ambientes para el
entrenamiento
Entrenamiento y
optimización del
modelo
Despliegue del
modelo en
producción
Administración y
escalamiento de
ambiente de
producción
Notebooks pre-
construidos para
problemas comunes
Algoritmos con alto
desempeño incluidos
© 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved.
AmazonSageMaker
Optimización
L l e v a n d o M a c h i n e L e a r n i n g a t o d o s l o s d e s a r r o l l a d o r e s
Recolección y
preparación de los datos
de entrenamiento
Selección y
optimización del
algoritmo
Preparación y
administración de
ambientes para el
entrenamiento
Entrenamiento y
optimización del
modelo
Despliegue del
modelo en
producción
Administración y
escalamiento de
ambiente de
producción
Notebooks pre-
construidos para
problemas comunes
Algoritmos con alto
desempeño incluidos
Entrenamiento con
un solo click
© 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved.
AmazonSageMaker
Despliegue con
un clic
L l e v a n d o M a c h i n e L e a r n i n g a t o d o s l o s d e s a r r o l l a d o r e s
Recolección y
preparación de los datos
de entrenamiento
Selección y
optimización del
algoritmo
Preparación y
administración de
ambientes para el
entrenamiento
Entrenamiento y
optimización del
modelo
Despliegue del
modelo en
producción
Administración y
escalamiento de
ambiente de
producción
Notebooks pre-
construidos para
problemas comunes
Algoritmos con alto
desempeño incluidos
Entrenamiento con
un solo click Optimización
© 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved.
AmazonSageMaker
Totalmente administrado
con auto-escalamiento,
verificación de estado,
reposición automática de
nodos fallidos y
verificaciones de seguridad
L l e v a n d o M a c h i n e L e a r n i n g a t o d o s l o s d e s a r r o l l a d o r e s
Recolección y
preparación de los datos
de entrenamiento
Selección y
optimización del
algoritmo
Preparación y
administración de
ambientes para el
entrenamiento
Entrenamiento y
optimización del
modelo
Despliegue del
modelo en
producción
Administración y
escalamiento de
ambiente de
producción
Notebooks pre-
construidos para
problemas comunes
Algoritmos con alto
desempeño incluidos
Entrenamiento con
un solo click Optimización
Despliegue con
un click
© 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved.
AmazonSageMaker -XGBoost
import sagemaker
import boto3
from sagemaker import get_execution_role
from sagemaker.amazon.amazon_estimator import get_image_uri
sess = sagemaker.Session()
role = get_execution_role()
container = get_image_uri(boto3.Session().region_name, 'xgboost', '0.90-1')
xgboost = sagemaker.estimator.Estimator(container,
role,
train_instance_count=1,
train_instance_type='ml.c5.xlarge',
output_path='s3://bucket/path/output',
sagemaker_session=sess)
xgboost.set_hyperparameters(max_depth=6, eta=0.3, gamma=0, min_child_weight=1,
subsample=1, silent=0, objective="reg:linear", num_round=120)
xgboost.fit({'train':'s3://bucket/path/training/data',
'test': 's3://bucket/path/test/data'})
© 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved.
AmazonSageMaker -XGBoost
import sagemaker
import boto3
from sagemaker import get_execution_role
from sagemaker.amazon.amazon_estimator import get_image_uri
sess = sagemaker.Session()
role = get_execution_role()
container = get_image_uri(boto3.Session().region_name, 'xgboost', '0.90-1')
xgboost = sagemaker.estimator.Estimator(container,
role,
train_instance_count=1,
train_instance_type='ml.c5.xlarge',
output_path='s3://bucket/path/output',
sagemaker_session=sess)
xgboost.set_hyperparameters(max_depth=6, eta=0.3, gamma=0, min_child_weight=1,
subsample=1, silent=0, objective="reg:linear", num_round=120)
xgboost.fit({'train':'s3://bucket/path/training/data',
'test': 's3://bucket/path/test/data'})
© 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved.
AmazonSageMaker -XGBoost
import sagemaker
import boto3
from sagemaker import get_execution_role
from sagemaker.amazon.amazon_estimator import get_image_uri
sess = sagemaker.Session()
role = get_execution_role()
container = get_image_uri(boto3.Session().region_name, 'xgboost', '0.90-1')
xgboost = sagemaker.estimator.Estimator(container,
role,
train_instance_count=1,
train_instance_type='ml.c5.xlarge',
output_path='s3://bucket/path/output',
sagemaker_session=sess)
xgboost.set_hyperparameters(max_depth=6, eta=0.3, gamma=0, min_child_weight=1,
subsample=1, silent=0, objective="reg:linear", num_round=120)
xgboost.fit({'train':'s3://bucket/path/training/data',
'test': 's3://bucket/path/test/data'})
© 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved.
AmazonSageMaker -XGBoost
import sagemaker
import boto3
from sagemaker import get_execution_role
from sagemaker.amazon.amazon_estimator import get_image_uri
sess = sagemaker.Session()
role = get_execution_role()
container = get_image_uri(boto3.Session().region_name, 'xgboost', '0.90-1')
xgboost = sagemaker.estimator.Estimator(container,
role,
train_instance_count=1,
train_instance_type='ml.c5.xlarge',
output_path='s3://bucket/path/output',
sagemaker_session=sess)
xgboost.set_hyperparameters(max_depth=6, eta=0.3, gamma=0, min_child_weight=1,
subsample=1, silent=0, objective="reg:linear", num_round=120)
xgboost.fit({'train':'s3://bucket/path/training/data',
'test': 's3://bucket/path/test/data'})
© 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved.
AmazonSageMaker -XGBoost
import sagemaker
import boto3
from sagemaker import get_execution_role
from sagemaker.amazon.amazon_estimator import get_image_uri
sess = sagemaker.Session()
role = get_execution_role()
container = get_image_uri(boto3.Session().region_name, 'xgboost', '0.90-1')
xgboost = sagemaker.estimator.Estimator(container,
role,
train_instance_count=1,
train_instance_type='ml.c5.xlarge',
output_path='s3://bucket/path/output',
sagemaker_session=sess)
xgboost.set_hyperparameters(max_depth=6, eta=0.3, gamma=0, min_child_weight=1,
subsample=1, silent=0, objective="reg:linear", num_round=120)
xgboost.fit({'train':'s3://bucket/path/training/data',
'test': 's3://bucket/path/test/data'})
© 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved.
AmazonSageMaker -XGBoost
import sagemaker
import boto3
from sagemaker import get_execution_role
from sagemaker.amazon.amazon_estimator import get_image_uri
sess = sagemaker.Session()
role = get_execution_role()
container = get_image_uri(boto3.Session().region_name, 'xgboost', '0.90-1')
xgboost = sagemaker.estimator.Estimator(container,
role,
train_instance_count=1,
train_instance_type='ml.c5.xlarge',
output_path='s3://bucket/path/output',
sagemaker_session=sess)
xgboost.set_hyperparameters(max_depth=6, eta=0.3, gamma=0, min_child_weight=1,
subsample=1, silent=0, objective="reg:linear", num_round=120)
xgboost.fit({'train':'s3://bucket/path/training/data',
'test': 's3://bucket/path/test/data'})
© 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved.
AmazonSageMaker -XGBoost
import sagemaker
import boto3
from sagemaker import get_execution_role
from sagemaker.amazon.amazon_estimator import get_image_uri
sess = sagemaker.Session()
role = get_execution_role()
container = get_image_uri(boto3.Session().region_name, 'xgboost', '0.90-1')
xgboost = sagemaker.estimator.Estimator(container,
role,
train_instance_count=1,
train_instance_type='ml.c5.xlarge',
output_path='s3://bucket/path/output',
sagemaker_session=sess)
xgboost.set_hyperparameters(max_depth=6, eta=0.3, gamma=0, min_child_weight=1,
subsample=1, silent=0, objective="reg:linear", num_round=120)
xgboost.fit({'train':'s3://bucket/path/training/data',
'test': 's3://bucket/path/test/data'})
© 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved.
AmazonSageMaker -XGBoost
xgboost_predictor = xgboost.deploy(initial_instance_count=1, instance_type='ml.m5.xlarge')
from sagemaker.predictor import csv_serializer, json_deserializer
xgboost_predictor.content_type = 'text/csv'
xgboost_predictor.serializer = csv_serializer
xgboost_predictor.deserializer = json_deserializer
result = xgboost_predictor.predict(val_df.sample(n=1))
print("prediction: {}".format(result))
© 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved.
AmazonSageMaker -XGBoost
xgboost_predictor = xgboost.deploy(initial_instance_count=1, instance_type='ml.m5.xlarge')
from sagemaker.predictor import csv_serializer, json_deserializer
xgboost_predictor.content_type = 'text/csv'
xgboost_predictor.serializer = csv_serializer
xgboost_predictor.deserializer = json_deserializer
result = xgboost_predictor.predict(val_df.sample(n=1))
print("prediction: {}".format(result))
© 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved.
AmazonSageMaker -XGBoost
xgboost_predictor = xgboost.deploy(initial_instance_count=1, instance_type='ml.m5.xlarge')
from sagemaker.predictor import csv_serializer, json_deserializer
xgboost_predictor.content_type = 'text/csv'
xgboost_predictor.serializer = csv_serializer
xgboost_predictor.deserializer = json_deserializer
result = xgboost_predictor.predict(val_df.sample(n=1))
print("prediction: {}".format(result))
© 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved.
AmazonSageMaker -XGBoost
xgboost_predictor = xgboost.deploy(initial_instance_count=1, instance_type='ml.m5.xlarge')
from sagemaker.predictor import csv_serializer, json_deserializer
xgboost_predictor.content_type = 'text/csv'
xgboost_predictor.serializer = csv_serializer
xgboost_predictor.deserializer = json_deserializer
result = xgboost_predictor.predict(val_df.sample(n=1))
print("prediction: {}".format(result))
© 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved.
AmazonSageMaker -XGBoost
xgboost_predictor = xgboost.deploy(initial_instance_count=1, instance_type='ml.m5.xlarge')
from sagemaker.predictor import csv_serializer, json_deserializer
xgboost_predictor.content_type = 'text/csv'
xgboost_predictor.serializer = csv_serializer
xgboost_predictor.deserializer = json_deserializer
result = xgboost_predictor.predict(val_df.sample(n=1))
print("prediction: {}".format(result))
¡Gracias!
© 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Edzon Sánchez
edzons@amazon.com

More Related Content

Similar to AWS Innovate 2020 - Cómo crear aplicaciones inteligentes con inteligencia artificial en AWS - Edzon Sanchez

Desafios da transição de estado em um mundo serverless
Desafios da transição de estado em um mundo serverlessDesafios da transição de estado em um mundo serverless
Desafios da transição de estado em um mundo serverlessAlex Barbosa Coqueiro
 
Demystifying Machine Learning on AWS
Demystifying Machine Learning on AWSDemystifying Machine Learning on AWS
Demystifying Machine Learning on AWSAmazon Web Services
 
20200714 AWS Black Belt Online Seminar Amazon Neptune
20200714 AWS Black Belt Online Seminar Amazon Neptune20200714 AWS Black Belt Online Seminar Amazon Neptune
20200714 AWS Black Belt Online Seminar Amazon NeptuneAmazon Web Services Japan
 
AWS 기반 인공지능 비디오 분석 서비스 소개::Ranju Das::AWS Summit Seoul 2018
AWS 기반 인공지능 비디오 분석 서비스 소개::Ranju Das::AWS Summit Seoul 2018AWS 기반 인공지능 비디오 분석 서비스 소개::Ranju Das::AWS Summit Seoul 2018
AWS 기반 인공지능 비디오 분석 서비스 소개::Ranju Das::AWS Summit Seoul 2018Amazon Web Services Korea
 
NEW LAUNCH! Amazon Rekognition Video eliminates manual cataloging of video wh...
NEW LAUNCH! Amazon Rekognition Video eliminates manual cataloging of video wh...NEW LAUNCH! Amazon Rekognition Video eliminates manual cataloging of video wh...
NEW LAUNCH! Amazon Rekognition Video eliminates manual cataloging of video wh...Amazon Web Services
 
Build Intelligent Apps Using AI Services.pdf
Build Intelligent Apps Using AI Services.pdfBuild Intelligent Apps Using AI Services.pdf
Build Intelligent Apps Using AI Services.pdfAmazon Web Services
 
Build Intelligent Apps Using AI Services
Build Intelligent Apps Using AI ServicesBuild Intelligent Apps Using AI Services
Build Intelligent Apps Using AI ServicesAmazon Web Services
 
AWS Innovate 2020 - Keynote Vinicius Senger
AWS Innovate 2020 - Keynote Vinicius Senger AWS Innovate 2020 - Keynote Vinicius Senger
AWS Innovate 2020 - Keynote Vinicius Senger Amazon Web Services LATAM
 
Increase the value of video using ML and AWS media services - SVC301 - Santa ...
Increase the value of video using ML and AWS media services - SVC301 - Santa ...Increase the value of video using ML and AWS media services - SVC301 - Santa ...
Increase the value of video using ML and AWS media services - SVC301 - Santa ...Amazon Web Services
 
Amazon EventBridge: AWS re:Invent Serverless London Recap Day
Amazon EventBridge: AWS re:Invent Serverless London Recap DayAmazon EventBridge: AWS re:Invent Serverless London Recap Day
Amazon EventBridge: AWS re:Invent Serverless London Recap DayJulian Wood
 
AWS re:Invent serverless recap day: Amazon EventBridge
AWS re:Invent serverless recap day: Amazon EventBridgeAWS re:Invent serverless recap day: Amazon EventBridge
AWS re:Invent serverless recap day: Amazon EventBridge⛷️ Ben Smith
 
Real-Time Personalized Customer Experiences at Bonobos (RET203) - AWS re:Inve...
Real-Time Personalized Customer Experiences at Bonobos (RET203) - AWS re:Inve...Real-Time Personalized Customer Experiences at Bonobos (RET203) - AWS re:Inve...
Real-Time Personalized Customer Experiences at Bonobos (RET203) - AWS re:Inve...Amazon Web Services
 
How to Get the Most Out of Amazon Rekognition Video, a deep learning based vi...
How to Get the Most Out of Amazon Rekognition Video, a deep learning based vi...How to Get the Most Out of Amazon Rekognition Video, a deep learning based vi...
How to Get the Most Out of Amazon Rekognition Video, a deep learning based vi...Amazon Web Services
 
Amazon Rekognition & Amazon Polly
Amazon Rekognition & Amazon PollyAmazon Rekognition & Amazon Polly
Amazon Rekognition & Amazon PollyAmazon Web Services
 
Demystifying Machine Learning on AWS
Demystifying Machine Learning on AWSDemystifying Machine Learning on AWS
Demystifying Machine Learning on AWSAmazon Web Services
 
Aggiungi funzionalita AI alle tue applicazioni con gli Amazon AI
Aggiungi funzionalita AI alle tue applicazioni con gli Amazon AIAggiungi funzionalita AI alle tue applicazioni con gli Amazon AI
Aggiungi funzionalita AI alle tue applicazioni con gli Amazon AIAmazon Web Services
 
Increasing the value of video with machine learning & AWS Media Services - SV...
Increasing the value of video with machine learning & AWS Media Services - SV...Increasing the value of video with machine learning & AWS Media Services - SV...
Increasing the value of video with machine learning & AWS Media Services - SV...Amazon Web Services
 
Building Intelligent Applications Using AI Services
Building Intelligent Applications Using AI ServicesBuilding Intelligent Applications Using AI Services
Building Intelligent Applications Using AI ServicesAmazon Web Services
 
AWS Summit Singapore 2019 | Accelerating ML Adoption with Our New AI services
AWS Summit Singapore 2019 | Accelerating ML Adoption with Our New AI servicesAWS Summit Singapore 2019 | Accelerating ML Adoption with Our New AI services
AWS Summit Singapore 2019 | Accelerating ML Adoption with Our New AI servicesAmazon Web Services
 

Similar to AWS Innovate 2020 - Cómo crear aplicaciones inteligentes con inteligencia artificial en AWS - Edzon Sanchez (20)

Desafios da transição de estado em um mundo serverless
Desafios da transição de estado em um mundo serverlessDesafios da transição de estado em um mundo serverless
Desafios da transição de estado em um mundo serverless
 
Demystifying Machine Learning on AWS
Demystifying Machine Learning on AWSDemystifying Machine Learning on AWS
Demystifying Machine Learning on AWS
 
20200714 AWS Black Belt Online Seminar Amazon Neptune
20200714 AWS Black Belt Online Seminar Amazon Neptune20200714 AWS Black Belt Online Seminar Amazon Neptune
20200714 AWS Black Belt Online Seminar Amazon Neptune
 
AWS 기반 인공지능 비디오 분석 서비스 소개::Ranju Das::AWS Summit Seoul 2018
AWS 기반 인공지능 비디오 분석 서비스 소개::Ranju Das::AWS Summit Seoul 2018AWS 기반 인공지능 비디오 분석 서비스 소개::Ranju Das::AWS Summit Seoul 2018
AWS 기반 인공지능 비디오 분석 서비스 소개::Ranju Das::AWS Summit Seoul 2018
 
NEW LAUNCH! Amazon Rekognition Video eliminates manual cataloging of video wh...
NEW LAUNCH! Amazon Rekognition Video eliminates manual cataloging of video wh...NEW LAUNCH! Amazon Rekognition Video eliminates manual cataloging of video wh...
NEW LAUNCH! Amazon Rekognition Video eliminates manual cataloging of video wh...
 
Build Intelligent Apps Using AI Services.pdf
Build Intelligent Apps Using AI Services.pdfBuild Intelligent Apps Using AI Services.pdf
Build Intelligent Apps Using AI Services.pdf
 
Build Intelligent Apps Using AI Services
Build Intelligent Apps Using AI ServicesBuild Intelligent Apps Using AI Services
Build Intelligent Apps Using AI Services
 
AWS Innovate 2020 - Keynote Vinicius Senger
AWS Innovate 2020 - Keynote Vinicius Senger AWS Innovate 2020 - Keynote Vinicius Senger
AWS Innovate 2020 - Keynote Vinicius Senger
 
Amazon Rekognition
Amazon RekognitionAmazon Rekognition
Amazon Rekognition
 
Increase the value of video using ML and AWS media services - SVC301 - Santa ...
Increase the value of video using ML and AWS media services - SVC301 - Santa ...Increase the value of video using ML and AWS media services - SVC301 - Santa ...
Increase the value of video using ML and AWS media services - SVC301 - Santa ...
 
Amazon EventBridge: AWS re:Invent Serverless London Recap Day
Amazon EventBridge: AWS re:Invent Serverless London Recap DayAmazon EventBridge: AWS re:Invent Serverless London Recap Day
Amazon EventBridge: AWS re:Invent Serverless London Recap Day
 
AWS re:Invent serverless recap day: Amazon EventBridge
AWS re:Invent serverless recap day: Amazon EventBridgeAWS re:Invent serverless recap day: Amazon EventBridge
AWS re:Invent serverless recap day: Amazon EventBridge
 
Real-Time Personalized Customer Experiences at Bonobos (RET203) - AWS re:Inve...
Real-Time Personalized Customer Experiences at Bonobos (RET203) - AWS re:Inve...Real-Time Personalized Customer Experiences at Bonobos (RET203) - AWS re:Inve...
Real-Time Personalized Customer Experiences at Bonobos (RET203) - AWS re:Inve...
 
How to Get the Most Out of Amazon Rekognition Video, a deep learning based vi...
How to Get the Most Out of Amazon Rekognition Video, a deep learning based vi...How to Get the Most Out of Amazon Rekognition Video, a deep learning based vi...
How to Get the Most Out of Amazon Rekognition Video, a deep learning based vi...
 
Amazon Rekognition & Amazon Polly
Amazon Rekognition & Amazon PollyAmazon Rekognition & Amazon Polly
Amazon Rekognition & Amazon Polly
 
Demystifying Machine Learning on AWS
Demystifying Machine Learning on AWSDemystifying Machine Learning on AWS
Demystifying Machine Learning on AWS
 
Aggiungi funzionalita AI alle tue applicazioni con gli Amazon AI
Aggiungi funzionalita AI alle tue applicazioni con gli Amazon AIAggiungi funzionalita AI alle tue applicazioni con gli Amazon AI
Aggiungi funzionalita AI alle tue applicazioni con gli Amazon AI
 
Increasing the value of video with machine learning & AWS Media Services - SV...
Increasing the value of video with machine learning & AWS Media Services - SV...Increasing the value of video with machine learning & AWS Media Services - SV...
Increasing the value of video with machine learning & AWS Media Services - SV...
 
Building Intelligent Applications Using AI Services
Building Intelligent Applications Using AI ServicesBuilding Intelligent Applications Using AI Services
Building Intelligent Applications Using AI Services
 
AWS Summit Singapore 2019 | Accelerating ML Adoption with Our New AI services
AWS Summit Singapore 2019 | Accelerating ML Adoption with Our New AI servicesAWS Summit Singapore 2019 | Accelerating ML Adoption with Our New AI services
AWS Summit Singapore 2019 | Accelerating ML Adoption with Our New AI services
 

More from Amazon Web Services LATAM

AWS para terceiro setor - Sessão 1 - Introdução à nuvem
AWS para terceiro setor - Sessão 1 - Introdução à nuvemAWS para terceiro setor - Sessão 1 - Introdução à nuvem
AWS para terceiro setor - Sessão 1 - Introdução à nuvemAmazon Web Services LATAM
 
AWS para terceiro setor - Sessão 2 - Armazenamento e Backup
AWS para terceiro setor - Sessão 2 - Armazenamento e BackupAWS para terceiro setor - Sessão 2 - Armazenamento e Backup
AWS para terceiro setor - Sessão 2 - Armazenamento e BackupAmazon Web Services LATAM
 
AWS para terceiro setor - Sessão 3 - Protegendo seus dados.
AWS para terceiro setor - Sessão 3 - Protegendo seus dados.AWS para terceiro setor - Sessão 3 - Protegendo seus dados.
AWS para terceiro setor - Sessão 3 - Protegendo seus dados.Amazon Web Services LATAM
 
AWS para terceiro setor - Sessão 1 - Introdução à nuvem
AWS para terceiro setor - Sessão 1 - Introdução à nuvemAWS para terceiro setor - Sessão 1 - Introdução à nuvem
AWS para terceiro setor - Sessão 1 - Introdução à nuvemAmazon Web Services LATAM
 
AWS para terceiro setor - Sessão 2 - Armazenamento e Backup
AWS para terceiro setor - Sessão 2 - Armazenamento e BackupAWS para terceiro setor - Sessão 2 - Armazenamento e Backup
AWS para terceiro setor - Sessão 2 - Armazenamento e BackupAmazon Web Services LATAM
 
AWS para terceiro setor - Sessão 3 - Protegendo seus dados.
AWS para terceiro setor - Sessão 3 - Protegendo seus dados.AWS para terceiro setor - Sessão 3 - Protegendo seus dados.
AWS para terceiro setor - Sessão 3 - Protegendo seus dados.Amazon Web Services LATAM
 
Automatice el proceso de entrega con CI/CD en AWS
Automatice el proceso de entrega con CI/CD en AWSAutomatice el proceso de entrega con CI/CD en AWS
Automatice el proceso de entrega con CI/CD en AWSAmazon Web Services LATAM
 
Automatize seu processo de entrega de software com CI/CD na AWS
Automatize seu processo de entrega de software com CI/CD na AWSAutomatize seu processo de entrega de software com CI/CD na AWS
Automatize seu processo de entrega de software com CI/CD na AWSAmazon Web Services LATAM
 
Ransomware: como recuperar os seus dados na nuvem AWS
Ransomware: como recuperar os seus dados na nuvem AWSRansomware: como recuperar os seus dados na nuvem AWS
Ransomware: como recuperar os seus dados na nuvem AWSAmazon Web Services LATAM
 
Ransomware: cómo recuperar sus datos en la nube de AWS
Ransomware: cómo recuperar sus datos en la nube de AWSRansomware: cómo recuperar sus datos en la nube de AWS
Ransomware: cómo recuperar sus datos en la nube de AWSAmazon Web Services LATAM
 
Aprenda a migrar y transferir datos al usar la nube de AWS
Aprenda a migrar y transferir datos al usar la nube de AWSAprenda a migrar y transferir datos al usar la nube de AWS
Aprenda a migrar y transferir datos al usar la nube de AWSAmazon Web Services LATAM
 
Aprenda como migrar e transferir dados ao utilizar a nuvem da AWS
Aprenda como migrar e transferir dados ao utilizar a nuvem da AWSAprenda como migrar e transferir dados ao utilizar a nuvem da AWS
Aprenda como migrar e transferir dados ao utilizar a nuvem da AWSAmazon Web Services LATAM
 
Cómo mover a un almacenamiento de archivos administrados
Cómo mover a un almacenamiento de archivos administradosCómo mover a un almacenamiento de archivos administrados
Cómo mover a un almacenamiento de archivos administradosAmazon Web Services LATAM
 
Os benefícios de migrar seus workloads de Big Data para a AWS
Os benefícios de migrar seus workloads de Big Data para a AWSOs benefícios de migrar seus workloads de Big Data para a AWS
Os benefícios de migrar seus workloads de Big Data para a AWSAmazon Web Services LATAM
 

More from Amazon Web Services LATAM (20)

AWS para terceiro setor - Sessão 1 - Introdução à nuvem
AWS para terceiro setor - Sessão 1 - Introdução à nuvemAWS para terceiro setor - Sessão 1 - Introdução à nuvem
AWS para terceiro setor - Sessão 1 - Introdução à nuvem
 
AWS para terceiro setor - Sessão 2 - Armazenamento e Backup
AWS para terceiro setor - Sessão 2 - Armazenamento e BackupAWS para terceiro setor - Sessão 2 - Armazenamento e Backup
AWS para terceiro setor - Sessão 2 - Armazenamento e Backup
 
AWS para terceiro setor - Sessão 3 - Protegendo seus dados.
AWS para terceiro setor - Sessão 3 - Protegendo seus dados.AWS para terceiro setor - Sessão 3 - Protegendo seus dados.
AWS para terceiro setor - Sessão 3 - Protegendo seus dados.
 
AWS para terceiro setor - Sessão 1 - Introdução à nuvem
AWS para terceiro setor - Sessão 1 - Introdução à nuvemAWS para terceiro setor - Sessão 1 - Introdução à nuvem
AWS para terceiro setor - Sessão 1 - Introdução à nuvem
 
AWS para terceiro setor - Sessão 2 - Armazenamento e Backup
AWS para terceiro setor - Sessão 2 - Armazenamento e BackupAWS para terceiro setor - Sessão 2 - Armazenamento e Backup
AWS para terceiro setor - Sessão 2 - Armazenamento e Backup
 
AWS para terceiro setor - Sessão 3 - Protegendo seus dados.
AWS para terceiro setor - Sessão 3 - Protegendo seus dados.AWS para terceiro setor - Sessão 3 - Protegendo seus dados.
AWS para terceiro setor - Sessão 3 - Protegendo seus dados.
 
Automatice el proceso de entrega con CI/CD en AWS
Automatice el proceso de entrega con CI/CD en AWSAutomatice el proceso de entrega con CI/CD en AWS
Automatice el proceso de entrega con CI/CD en AWS
 
Automatize seu processo de entrega de software com CI/CD na AWS
Automatize seu processo de entrega de software com CI/CD na AWSAutomatize seu processo de entrega de software com CI/CD na AWS
Automatize seu processo de entrega de software com CI/CD na AWS
 
Cómo empezar con Amazon EKS
Cómo empezar con Amazon EKSCómo empezar con Amazon EKS
Cómo empezar con Amazon EKS
 
Como começar com Amazon EKS
Como começar com Amazon EKSComo começar com Amazon EKS
Como começar com Amazon EKS
 
Ransomware: como recuperar os seus dados na nuvem AWS
Ransomware: como recuperar os seus dados na nuvem AWSRansomware: como recuperar os seus dados na nuvem AWS
Ransomware: como recuperar os seus dados na nuvem AWS
 
Ransomware: cómo recuperar sus datos en la nube de AWS
Ransomware: cómo recuperar sus datos en la nube de AWSRansomware: cómo recuperar sus datos en la nube de AWS
Ransomware: cómo recuperar sus datos en la nube de AWS
 
Ransomware: Estratégias de Mitigação
Ransomware: Estratégias de MitigaçãoRansomware: Estratégias de Mitigação
Ransomware: Estratégias de Mitigação
 
Ransomware: Estratégias de Mitigación
Ransomware: Estratégias de MitigaciónRansomware: Estratégias de Mitigación
Ransomware: Estratégias de Mitigación
 
Aprenda a migrar y transferir datos al usar la nube de AWS
Aprenda a migrar y transferir datos al usar la nube de AWSAprenda a migrar y transferir datos al usar la nube de AWS
Aprenda a migrar y transferir datos al usar la nube de AWS
 
Aprenda como migrar e transferir dados ao utilizar a nuvem da AWS
Aprenda como migrar e transferir dados ao utilizar a nuvem da AWSAprenda como migrar e transferir dados ao utilizar a nuvem da AWS
Aprenda como migrar e transferir dados ao utilizar a nuvem da AWS
 
Cómo mover a un almacenamiento de archivos administrados
Cómo mover a un almacenamiento de archivos administradosCómo mover a un almacenamiento de archivos administrados
Cómo mover a un almacenamiento de archivos administrados
 
Simplifique su BI con AWS
Simplifique su BI con AWSSimplifique su BI con AWS
Simplifique su BI con AWS
 
Simplifique o seu BI com a AWS
Simplifique o seu BI com a AWSSimplifique o seu BI com a AWS
Simplifique o seu BI com a AWS
 
Os benefícios de migrar seus workloads de Big Data para a AWS
Os benefícios de migrar seus workloads de Big Data para a AWSOs benefícios de migrar seus workloads de Big Data para a AWS
Os benefícios de migrar seus workloads de Big Data para a AWS
 

Recently uploaded

Designing IA for AI - Information Architecture Conference 2024
Designing IA for AI - Information Architecture Conference 2024Designing IA for AI - Information Architecture Conference 2024
Designing IA for AI - Information Architecture Conference 2024Enterprise Knowledge
 
Unlocking the Potential of the Cloud for IBM Power Systems
Unlocking the Potential of the Cloud for IBM Power SystemsUnlocking the Potential of the Cloud for IBM Power Systems
Unlocking the Potential of the Cloud for IBM Power SystemsPrecisely
 
Connect Wave/ connectwave Pitch Deck Presentation
Connect Wave/ connectwave Pitch Deck PresentationConnect Wave/ connectwave Pitch Deck Presentation
Connect Wave/ connectwave Pitch Deck PresentationSlibray Presentation
 
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...Patryk Bandurski
 
Maximizing Board Effectiveness 2024 Webinar.pptx
Maximizing Board Effectiveness 2024 Webinar.pptxMaximizing Board Effectiveness 2024 Webinar.pptx
Maximizing Board Effectiveness 2024 Webinar.pptxOnBoard
 
Artificial intelligence in the post-deep learning era
Artificial intelligence in the post-deep learning eraArtificial intelligence in the post-deep learning era
Artificial intelligence in the post-deep learning eraDeakin University
 
Understanding the Laravel MVC Architecture
Understanding the Laravel MVC ArchitectureUnderstanding the Laravel MVC Architecture
Understanding the Laravel MVC ArchitecturePixlogix Infotech
 
SIEMENS: RAPUNZEL – A Tale About Knowledge Graph
SIEMENS: RAPUNZEL – A Tale About Knowledge GraphSIEMENS: RAPUNZEL – A Tale About Knowledge Graph
SIEMENS: RAPUNZEL – A Tale About Knowledge GraphNeo4j
 
"Federated learning: out of reach no matter how close",Oleksandr Lapshyn
"Federated learning: out of reach no matter how close",Oleksandr Lapshyn"Federated learning: out of reach no matter how close",Oleksandr Lapshyn
"Federated learning: out of reach no matter how close",Oleksandr LapshynFwdays
 
Injustice - Developers Among Us (SciFiDevCon 2024)
Injustice - Developers Among Us (SciFiDevCon 2024)Injustice - Developers Among Us (SciFiDevCon 2024)
Injustice - Developers Among Us (SciFiDevCon 2024)Allon Mureinik
 
Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024Scott Keck-Warren
 
AI as an Interface for Commercial Buildings
AI as an Interface for Commercial BuildingsAI as an Interface for Commercial Buildings
AI as an Interface for Commercial BuildingsMemoori
 
Transcript: New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024Transcript: New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024BookNet Canada
 
Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...
Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...
Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...shyamraj55
 
SQL Database Design For Developers at php[tek] 2024
SQL Database Design For Developers at php[tek] 2024SQL Database Design For Developers at php[tek] 2024
SQL Database Design For Developers at php[tek] 2024Scott Keck-Warren
 
Key Features Of Token Development (1).pptx
Key  Features Of Token  Development (1).pptxKey  Features Of Token  Development (1).pptx
Key Features Of Token Development (1).pptxLBM Solutions
 
APIForce Zurich 5 April Automation LPDG
APIForce Zurich 5 April  Automation LPDGAPIForce Zurich 5 April  Automation LPDG
APIForce Zurich 5 April Automation LPDGMarianaLemus7
 
Pigging Solutions Piggable Sweeping Elbows
Pigging Solutions Piggable Sweeping ElbowsPigging Solutions Piggable Sweeping Elbows
Pigging Solutions Piggable Sweeping ElbowsPigging Solutions
 

Recently uploaded (20)

Designing IA for AI - Information Architecture Conference 2024
Designing IA for AI - Information Architecture Conference 2024Designing IA for AI - Information Architecture Conference 2024
Designing IA for AI - Information Architecture Conference 2024
 
Unlocking the Potential of the Cloud for IBM Power Systems
Unlocking the Potential of the Cloud for IBM Power SystemsUnlocking the Potential of the Cloud for IBM Power Systems
Unlocking the Potential of the Cloud for IBM Power Systems
 
Connect Wave/ connectwave Pitch Deck Presentation
Connect Wave/ connectwave Pitch Deck PresentationConnect Wave/ connectwave Pitch Deck Presentation
Connect Wave/ connectwave Pitch Deck Presentation
 
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
 
DMCC Future of Trade Web3 - Special Edition
DMCC Future of Trade Web3 - Special EditionDMCC Future of Trade Web3 - Special Edition
DMCC Future of Trade Web3 - Special Edition
 
Maximizing Board Effectiveness 2024 Webinar.pptx
Maximizing Board Effectiveness 2024 Webinar.pptxMaximizing Board Effectiveness 2024 Webinar.pptx
Maximizing Board Effectiveness 2024 Webinar.pptx
 
Artificial intelligence in the post-deep learning era
Artificial intelligence in the post-deep learning eraArtificial intelligence in the post-deep learning era
Artificial intelligence in the post-deep learning era
 
Understanding the Laravel MVC Architecture
Understanding the Laravel MVC ArchitectureUnderstanding the Laravel MVC Architecture
Understanding the Laravel MVC Architecture
 
SIEMENS: RAPUNZEL – A Tale About Knowledge Graph
SIEMENS: RAPUNZEL – A Tale About Knowledge GraphSIEMENS: RAPUNZEL – A Tale About Knowledge Graph
SIEMENS: RAPUNZEL – A Tale About Knowledge Graph
 
"Federated learning: out of reach no matter how close",Oleksandr Lapshyn
"Federated learning: out of reach no matter how close",Oleksandr Lapshyn"Federated learning: out of reach no matter how close",Oleksandr Lapshyn
"Federated learning: out of reach no matter how close",Oleksandr Lapshyn
 
Injustice - Developers Among Us (SciFiDevCon 2024)
Injustice - Developers Among Us (SciFiDevCon 2024)Injustice - Developers Among Us (SciFiDevCon 2024)
Injustice - Developers Among Us (SciFiDevCon 2024)
 
Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024
 
AI as an Interface for Commercial Buildings
AI as an Interface for Commercial BuildingsAI as an Interface for Commercial Buildings
AI as an Interface for Commercial Buildings
 
Transcript: New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024Transcript: New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024
 
Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...
Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...
Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...
 
SQL Database Design For Developers at php[tek] 2024
SQL Database Design For Developers at php[tek] 2024SQL Database Design For Developers at php[tek] 2024
SQL Database Design For Developers at php[tek] 2024
 
Key Features Of Token Development (1).pptx
Key  Features Of Token  Development (1).pptxKey  Features Of Token  Development (1).pptx
Key Features Of Token Development (1).pptx
 
E-Vehicle_Hacking_by_Parul Sharma_null_owasp.pptx
E-Vehicle_Hacking_by_Parul Sharma_null_owasp.pptxE-Vehicle_Hacking_by_Parul Sharma_null_owasp.pptx
E-Vehicle_Hacking_by_Parul Sharma_null_owasp.pptx
 
APIForce Zurich 5 April Automation LPDG
APIForce Zurich 5 April  Automation LPDGAPIForce Zurich 5 April  Automation LPDG
APIForce Zurich 5 April Automation LPDG
 
Pigging Solutions Piggable Sweeping Elbows
Pigging Solutions Piggable Sweeping ElbowsPigging Solutions Piggable Sweeping Elbows
Pigging Solutions Piggable Sweeping Elbows
 

AWS Innovate 2020 - Cómo crear aplicaciones inteligentes con inteligencia artificial en AWS - Edzon Sanchez

  • 1.
  • 2. © 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved. Cómo crear aplicaciones inteligentes con inteligencia artificial en AWS Edzon Sánchez Machine Learning Specialist
  • 3. © 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved. VISIÓN SPEECH TEXTO BÚSQUEDAS CHATBOTS PERSONALIZACIÓN PRONÓSTICOS FRAUDES DESARROLLO CENTROS DE CONTACTO Stackde servicios deAI/MachineLearning SERVICIOS DE INTELIGENCIA ARTIFICIAL Amazon Rekognition Amazon Polly Amazon Transcribe +Medical Amazon Comprehend +Medical Amazon Translate Amazon Lex Amazon Personalize Amazon Forecast Amazon Fraud Detector Amazon CodeGuru Amazon Textract Amazon Kendra Contact Lens For Amazon Connect ¡Nuevo! ¡Nuevo! ¡Nuevo! ¡Nuevo!
  • 4. © 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved. VISIÓN SPEECH TEXTO BÚSQUEDAS CHATBOTS PERSONALIZACIÓN PRONÓSTICOS FRAUDES DESARROLLO CENTROS DE CONTACTO Stackde servicios deAI/MachineLearning SERVICIOS DE INTELIGENCIA ARTIFICIAL Amazon Rekognition Amazon Polly Amazon Transcribe +Medical Amazon Comprehend +Medical Amazon Translate Amazon Lex Amazon Personalize Amazon Forecast Amazon Fraud Detector Amazon CodeGuru Amazon Textract Amazon Kendra Contact Lens For Amazon Connect ¡Nuevo! ¡Nuevo! ¡Nuevo! ¡Nuevo! ¡Nuevo! Ground Truth Augmented AI ML Marketplace Neo Algoritmos incluidos Notebooks Experiments Entrenamiento y optimización de modelos Debugger Autopilot Hosting de modelos Model Monitor SERVICIOS DE MACHINE LEARNING SageMaker Studio IDE ¡Nuevo! ¡Nuevo! ¡Nuevo! ¡Nuevo! ¡Nuevo! ¡Nuevo! Amazon SageMaker
  • 5. © 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved. VISIÓN SPEECH TEXTO BÚSQUEDAS CHATBOTS PERSONALIZACIÓN PRONÓSTICOS FRAUDES DESARROLLO CENTROS DE CONTACTO Stackde servicios deAI/MachineLearning SERVICIOS DE INTELIGENCIA ARTIFICIAL Amazon Rekognition Amazon Polly Amazon Transcribe +Medical Amazon Comprehend +Medical Amazon Translate Amazon Lex Amazon Personalize Amazon Forecast Amazon Fraud Detector Amazon CodeGuru Amazon Textract Amazon Kendra Contact Lens For Amazon Connect ¡Nuevo! ¡Nuevo! ¡Nuevo! ¡Nuevo! ¡Nuevo! Ground Truth Augmented AI ML Marketplace Neo Algoritmos incluidos Notebooks Experiments Entrenamiento y optimización de modelos Debugger Autopilot Hosting de modelos Model Monitor Deep Learning AMIs & Containers GPUs & CPUs Elastic Inference Inferentia FPGA SERVICIOS DE MACHINE LEARNING ML FRAMEWORKS E INFRASTRUCTURA SageMaker Studio IDE ¡Nuevo! ¡Nuevo! ¡Nuevo! ¡Nuevo! ¡Nuevo! ¡Nuevo! Amazon SageMaker
  • 6. © 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved.
  • 7. © 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Rekognition Reconocimiento de objetos, escenas y actividades Reconocimiento facial Análisis facial Rastreo de personas Detección de contenido no apropiado Reconocimiento de celebridades Texto en imágenes A n á l i s i s d e i m á g e n e s y v i d e o b a s a d o e n D e e p l e a r n i n g
  • 8. © 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved. import boto3 region = boto3.Session().region_name rekognition=boto3.client(service_name='rekognition', region_name=region) bucket='bucket' photo='photo.jpg' response = rekognition.detect_labels( Image={'S3Object':{'Bucket':bucket,'Name':photo}}, MaxLabels=10, MinConfidence=0.8) print('Detected labels for ' + photo) for label in response['Labels']: print ("Label: " + label['Name']) print ("Confidence: " + str(label['Confidence'])) print ("Instances:") for instance in label['Instances']: print (" Bounding box") print (" Top: " + str(instance['BoundingBox']['Top'])) print (" Left: " + str(instance['BoundingBox']['Left'])) print (" Width: " + str(instance['BoundingBox']['Width'])) print (" Height: " + str(instance['BoundingBox']['Height'])) print (" Confidence: " + str(instance['Confidence'])) Amazon Rekognition -Python
  • 9. © 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved. import boto3 region = boto3.Session().region_name rekognition=boto3.client(service_name='rekognition', region_name=region) bucket='bucket' photo='photo.jpg' response = rekognition.detect_labels( Image={'S3Object':{'Bucket':bucket,'Name':photo}}, MaxLabels=10, MinConfidence=0.8) print('Detected labels for ' + photo) for label in response['Labels']: print ("Label: " + label['Name']) print ("Confidence: " + str(label['Confidence'])) print ("Instances:") for instance in label['Instances']: print (" Bounding box") print (" Top: " + str(instance['BoundingBox']['Top'])) print (" Left: " + str(instance['BoundingBox']['Left'])) print (" Width: " + str(instance['BoundingBox']['Width'])) print (" Height: " + str(instance['BoundingBox']['Height'])) print (" Confidence: " + str(instance['Confidence'])) Amazon Rekognition -Python
  • 10. © 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved. import boto3 region = boto3.Session().region_name rekognition=boto3.client(service_name='rekognition', region_name=region) bucket='bucket' photo='photo.jpg' response = rekognition.detect_labels( Image={'S3Object':{'Bucket':bucket,'Name':photo}}, MaxLabels=10, MinConfidence=0.8) print('Detected labels for ' + photo) for label in response['Labels']: print ("Label: " + label['Name']) print ("Confidence: " + str(label['Confidence'])) print ("Instances:") for instance in label['Instances']: print (" Bounding box") print (" Top: " + str(instance['BoundingBox']['Top'])) print (" Left: " + str(instance['BoundingBox']['Left'])) print (" Width: " + str(instance['BoundingBox']['Width'])) print (" Height: " + str(instance['BoundingBox']['Height'])) print (" Confidence: " + str(instance['Confidence'])) Amazon Rekognition -Python
  • 11. © 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved. import boto3 region = boto3.Session().region_name rekognition=boto3.client(service_name='rekognition', region_name=region) bucket='bucket' photo='photo.jpg' response = rekognition.detect_labels( Image={'S3Object':{'Bucket':bucket,'Name':photo}}, MaxLabels=10, MinConfidence=0.8) print('Detected labels for ' + photo) for label in response['Labels']: print ("Label: " + label['Name']) print ("Confidence: " + str(label['Confidence'])) print ("Instances:") for instance in label['Instances']: print (" Bounding box") print (" Top: " + str(instance['BoundingBox']['Top'])) print (" Left: " + str(instance['BoundingBox']['Left'])) print (" Width: " + str(instance['BoundingBox']['Width'])) print (" Height: " + str(instance['BoundingBox']['Height'])) print (" Confidence: " + str(instance['Confidence'])) Amazon Rekognition -Python
  • 12. © 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved. import boto3 region = boto3.Session().region_name rekognition=boto3.client(service_name='rekognition', region_name=region) bucket='bucket' photo='photo.jpg' response = rekognition.detect_labels( Image={'S3Object':{'Bucket':bucket,'Name':photo}}, MaxLabels=10, MinConfidence=0.8) print('Detected labels for ' + photo) for label in response['Labels']: print ("Label: " + label['Name']) print ("Confidence: " + str(label['Confidence'])) print ("Instances:") for instance in label['Instances']: print (" Bounding box") print (" Top: " + str(instance['BoundingBox']['Top'])) print (" Left: " + str(instance['BoundingBox']['Left'])) print (" Width: " + str(instance['BoundingBox']['Width'])) print (" Height: " + str(instance['BoundingBox']['Height'])) print (" Confidence: " + str(instance['Confidence'])) Amazon Rekognition -Python
  • 13. © 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Rekognition -Pythonimport boto3 region = boto3.Session().region_name rekognition=boto3.client(service_name='rekognition', region_name=region) bucket='bucket' photo='photo.jpg' response = rekognition.detect_labels( Image={'S3Object':{'Bucket':bucket,'Name':photo}}, MaxLabels=10, MinConfidence=0.8) print('Detected labels for ' + photo) for label in response['Labels']: print ("Label: " + label['Name']) print ("Confidence: " + str(label['Confidence'])) print ("Instances:") for instance in label['Instances']: print (" Bounding box") print (" Top: " + str(instance['BoundingBox']['Top'])) print (" Left: " + str(instance['BoundingBox']['Left'])) print (" Width: " + str(instance['BoundingBox']['Width'])) print (" Height: " + str(instance['BoundingBox']['Height'])) print (" Confidence: " + str(instance['Confidence']))
  • 14. © 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved. AmazonTranscribe C o n v e r s i ó n a u t o m á t i c a d e v o z e n t e x t o p r e c i s o y g r a m a t i c a l m e n t e c o r r e c t o Soporte para audio telefónico Time stamps a nivel de palabra Puntuación y formato automático Identificación de interlocutor Vocabulario personalizado Multiples idiomas
  • 15. © 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved. AmazonTranslate Tr a d u c c i ó n c o n f l u i d e z n a t u r a l Reconocimiento automático de idioma Análisis en batchTraducción en tiempo-real
  • 16. © 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Polly C o n v i e r t e t e x t o e n v o z q u e p a r e c e n a t u r a l , u t i l i z a n d o d e e p l e a r n i n g Amplia selección de voces e idiomas Voz sincronizable Fino control granular Reproducción ilimitada
  • 17. © 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved. AmazonComprehend D e s c u b r e i n f o r m a c i ó n r e l e v a n t e y r e l a c i o n e s e n e l t e x t o Amazon Comprehend Entidades Frases clave Idioma Sentimiento Modelado de tópico
  • 18. © 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved. AmazonComprehend -Python import boto3 import json region = boto3.Session().region_name comprehend = boto3.client(service_name='comprehend', region_name=region) text = 'Amazon.com, Inc localizado en Seattle, WA fue fundado el 5 de Julio de 1994 por Jeff Bezos' lang = comprehend.detect_dominant_language(Text=text) response = comprehend.detect_entities(Text=text, LanguageCode=lang) print(json.dumps(response, sort_keys=True, indent=4)) response = comprehend.detect_key_phrases(Text=text, LanguageCode=lang) print(json.dumps(response, sort_keys=True, indent=4)) response = comprehend.detect_sentiment(Text=text, LanguageCode=lang) print(json.dumps(response, sort_keys=True, indent=4))
  • 19. © 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved. AmazonComprehend -Python import boto3 import json region = boto3.Session().region_name comprehend = boto3.client(service_name='comprehend', region_name=region) text = 'Amazon.com, Inc localizado en Seattle, WA fue fundado el 5 de Julio de 1994 por Jeff Bezos' lang = comprehend.detect_dominant_language(Text=text) response = comprehend.detect_entities(Text=text, LanguageCode=lang) print(json.dumps(response, sort_keys=True, indent=4)) response = comprehend.detect_key_phrases(Text=text, LanguageCode=lang) print(json.dumps(response, sort_keys=True, indent=4)) response = comprehend.detect_sentiment(Text=text, LanguageCode=lang) print(json.dumps(response, sort_keys=True, indent=4))
  • 20. © 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved. AmazonComprehend -Python import boto3 import json region = boto3.Session().region_name comprehend = boto3.client(service_name='comprehend', region_name=region) text = 'Amazon.com, Inc localizado en Seattle, WA fue fundado el 5 de Julio de 1994 por Jeff Bezos' lang = comprehend.detect_dominant_language(Text=text) response = comprehend.detect_entities(Text=text, LanguageCode=lang) print(json.dumps(response, sort_keys=True, indent=4)) response = comprehend.detect_key_phrases(Text=text, LanguageCode=lang) print(json.dumps(response, sort_keys=True, indent=4)) response = comprehend.detect_sentiment(Text=text, LanguageCode=lang) print(json.dumps(response, sort_keys=True, indent=4))
  • 21. © 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved. AmazonComprehend -Python import boto3 import json region = boto3.Session().region_name comprehend = boto3.client(service_name='comprehend', region_name=region) text = 'Amazon.com, Inc localizado en Seattle, WA fue fundado el 5 de Julio de 1994 por Jeff Bezos' lang = comprehend.detect_dominant_language(Text=text) response = comprehend.detect_entities(Text=text, LanguageCode=lang) print(json.dumps(response, sort_keys=True, indent=4)) response = comprehend.detect_key_phrases(Text=text, LanguageCode=lang) print(json.dumps(response, sort_keys=True, indent=4)) response = comprehend.detect_sentiment(Text=text, LanguageCode=lang) print(json.dumps(response, sort_keys=True, indent=4))
  • 22. © 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved. AmazonComprehend -Python import boto3 import json region = boto3.Session().region_name comprehend = boto3.client(service_name='comprehend', region_name=region) text = 'Amazon.com, Inc localizado en Seattle, WA fue fundado el 5 de Julio de 1994 por Jeff Bezos' lang = comprehend.detect_dominant_language(Text=text) response = comprehend.detect_entities(Text=text, LanguageCode=lang) print(json.dumps(response, sort_keys=True, indent=4)) response = comprehend.detect_key_phrases(Text=text, LanguageCode=lang) print(json.dumps(response, sort_keys=True, indent=4)) response = comprehend.detect_sentiment(Text=text, LanguageCode=lang) print(json.dumps(response, sort_keys=True, indent=4))
  • 23. © 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved. AmazonComprehend -Python import boto3 import json region = boto3.Session().region_name comprehend = boto3.client(service_name='comprehend', region_name=region) text = 'Amazon.com, Inc localizado en Seattle, WA fue fundado el 5 de Julio de 1994 por Jeff Bezos' lang = comprehend.detect_dominant_language(Text=text) response = comprehend.detect_entities(Text=text, LanguageCode=lang) print(json.dumps(response, sort_keys=True, indent=4)) response = comprehend.detect_key_phrases(Text=text, LanguageCode=lang) print(json.dumps(response, sort_keys=True, indent=4)) response = comprehend.detect_sentiment(Text=text, LanguageCode=lang) print(json.dumps(response, sort_keys=True, indent=4))
  • 24. © 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved. AmazonComprehend -Python import boto3 import json region = boto3.Session().region_name comprehend = boto3.client(service_name='comprehend', region_name=region) text = 'Amazon.com, Inc localizado en Seattle, WA fue fundado el 5 de Julio de 1994 por Jeff Bezos' lang = comprehend.detect_dominant_language(Text=text) response = comprehend.detect_entities(Text=text, LanguageCode=lang) print(json.dumps(response, sort_keys=True, indent=4)) response = comprehend.detect_key_phrases(Text=text, LanguageCode=lang) print(json.dumps(response, sort_keys=True, indent=4)) response = comprehend.detect_sentiment(Text=text, LanguageCode=lang) print(json.dumps(response, sort_keys=True, indent=4))
  • 25. © 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Lex R e c o n o c i m i e n t o a u t o m á t i c o d e v o z p a r a c o n s t r u i r a p l i c a c i o n e s c o n v e r s a c i o n a l e s Desarrollo integrado a la consola AWS Invoca funciones Lambda Conversaciones de multiples pasos Despliegue con un clic Conectores empresariales Totalmente administrado
  • 26. © 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved. Elimina esfuerzo manual Disminuye los costos de procesamiento de documentos P R I N C I PA L E S C A R A C T E R Í S T I C A S Extrae datos de manera rápida y exacta Reconocimiento Óptico de Caracteres (OCR) Detección de pares llave-valor Umbrales de confianza ajustables Detección de tablas Cuadros delimitadores No se require experiencia en ML E x t r a e t e x t o y d a t o s d e v i r t u a l m e n t e c u a l q u i e r d o c u m e n t o AmazonTextract
  • 27. © 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved. Fácil de utilizar, desde la consola y el API Funciona con cualquier serie de tiempo histórica P R I N C I PA L E S C A R A C T E R Í S T I C A S Pronósticos más exactos que integran datos externos Considera múltiples series de tiempo a la vez Machine Learning automático Visualiza los pronósticos en la consola e importa a aplicaciones de negocio Evalúa la exactitud del modelo a través de la consola Calendariza los pronósticos y el re- entrenamiento Integra algoritmos existentes de Amazon SageMaker Amazon Forecast M e j o r a l a e x a c t i t u d d e l a s p r e d i c c i o n e s h a s t a u n 5 0 % a u n 1 / 1 0 d e l c o s t o
  • 28. © 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved. Tiempo-real Funciona con casi cualquier product o contenido Responde a los cambios de intención Machine Learning automático Integra algoritmos existentes de Amazon SageMaker Entrega recomendaciones de alta calidad Algoritmos de Deep Learning Fácil de utilizar Amazon Personalize M e j o r a l a e x p e r i e n c i a d e l o s c l i e n t e s c o n r e c o m e n d a c i o n e s y p e r s o n a l i z a c i ó n P R I N C I PA L E S C A R A C T E R Í S T I C A S
  • 29. © 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved.
  • 30. © 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved. AmazonSageMaker L l e v a n d o M a c h i n e L e a r n i n g a t o d o s l o s d e s a r r o l l a d o r e s Recolección y preparación de los datos de entrenamiento Selección y optimización del algoritmo Preparación y administración de ambientes para el entrenamiento Entrenamiento y optimización del modelo Despliegue del modelo en producción Administración y escalamiento de ambiente de producción
  • 31. © 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved. AmazonSageMaker Recolección y preparación de los datos de entrenamiento Selección y optimización del algoritmo Preparación y administración de ambientes para el entrenamiento Entrenamiento y optimización del modelo Despliegue del modelo en producción Administración y escalamiento de ambiente de producción Notebooks pre- construidos para problemas comunes L l e v a n d o M a c h i n e L e a r n i n g a t o d o s l o s d e s a r r o l l a d o r e s
  • 32. © 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved. AmazonSageMaker • K-Means Clustering • Principal Component Analysis • Neural Topic Modelling • Factorization Machines • Linear Learner (Regression) • BlazingText • Reinforcement learning • XGBoost • Topic Modeling (LDA) • Image Classification • Seq2Seq • Linear Learner (Classification) • DeepAR Forecasting L l e v a n d o M a c h i n e L e a r n i n g a t o d o s l o s d e s a r r o l l a d o r e s Recolección y preparación de los datos de entrenamiento Selección y optimización del algoritmo Notebooks pre- construidos para problemas comunes Algoritmos con alto desempeño incluidos
  • 33. © 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved. AmazonSageMaker Entrenamiento con un solo clic L l e v a n d o M a c h i n e L e a r n i n g a t o d o s l o s d e s a r r o l l a d o r e s Recolección y preparación de los datos de entrenamiento Selección y optimización del algoritmo Preparación y administración de ambientes para el entrenamiento Entrenamiento y optimización del modelo Despliegue del modelo en producción Administración y escalamiento de ambiente de producción Notebooks pre- construidos para problemas comunes Algoritmos con alto desempeño incluidos
  • 34. © 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved. AmazonSageMaker Optimización L l e v a n d o M a c h i n e L e a r n i n g a t o d o s l o s d e s a r r o l l a d o r e s Recolección y preparación de los datos de entrenamiento Selección y optimización del algoritmo Preparación y administración de ambientes para el entrenamiento Entrenamiento y optimización del modelo Despliegue del modelo en producción Administración y escalamiento de ambiente de producción Notebooks pre- construidos para problemas comunes Algoritmos con alto desempeño incluidos Entrenamiento con un solo click
  • 35. © 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved. AmazonSageMaker Despliegue con un clic L l e v a n d o M a c h i n e L e a r n i n g a t o d o s l o s d e s a r r o l l a d o r e s Recolección y preparación de los datos de entrenamiento Selección y optimización del algoritmo Preparación y administración de ambientes para el entrenamiento Entrenamiento y optimización del modelo Despliegue del modelo en producción Administración y escalamiento de ambiente de producción Notebooks pre- construidos para problemas comunes Algoritmos con alto desempeño incluidos Entrenamiento con un solo click Optimización
  • 36. © 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved. AmazonSageMaker Totalmente administrado con auto-escalamiento, verificación de estado, reposición automática de nodos fallidos y verificaciones de seguridad L l e v a n d o M a c h i n e L e a r n i n g a t o d o s l o s d e s a r r o l l a d o r e s Recolección y preparación de los datos de entrenamiento Selección y optimización del algoritmo Preparación y administración de ambientes para el entrenamiento Entrenamiento y optimización del modelo Despliegue del modelo en producción Administración y escalamiento de ambiente de producción Notebooks pre- construidos para problemas comunes Algoritmos con alto desempeño incluidos Entrenamiento con un solo click Optimización Despliegue con un click
  • 37. © 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved. AmazonSageMaker -XGBoost import sagemaker import boto3 from sagemaker import get_execution_role from sagemaker.amazon.amazon_estimator import get_image_uri sess = sagemaker.Session() role = get_execution_role() container = get_image_uri(boto3.Session().region_name, 'xgboost', '0.90-1') xgboost = sagemaker.estimator.Estimator(container, role, train_instance_count=1, train_instance_type='ml.c5.xlarge', output_path='s3://bucket/path/output', sagemaker_session=sess) xgboost.set_hyperparameters(max_depth=6, eta=0.3, gamma=0, min_child_weight=1, subsample=1, silent=0, objective="reg:linear", num_round=120) xgboost.fit({'train':'s3://bucket/path/training/data', 'test': 's3://bucket/path/test/data'})
  • 38. © 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved. AmazonSageMaker -XGBoost import sagemaker import boto3 from sagemaker import get_execution_role from sagemaker.amazon.amazon_estimator import get_image_uri sess = sagemaker.Session() role = get_execution_role() container = get_image_uri(boto3.Session().region_name, 'xgboost', '0.90-1') xgboost = sagemaker.estimator.Estimator(container, role, train_instance_count=1, train_instance_type='ml.c5.xlarge', output_path='s3://bucket/path/output', sagemaker_session=sess) xgboost.set_hyperparameters(max_depth=6, eta=0.3, gamma=0, min_child_weight=1, subsample=1, silent=0, objective="reg:linear", num_round=120) xgboost.fit({'train':'s3://bucket/path/training/data', 'test': 's3://bucket/path/test/data'})
  • 39. © 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved. AmazonSageMaker -XGBoost import sagemaker import boto3 from sagemaker import get_execution_role from sagemaker.amazon.amazon_estimator import get_image_uri sess = sagemaker.Session() role = get_execution_role() container = get_image_uri(boto3.Session().region_name, 'xgboost', '0.90-1') xgboost = sagemaker.estimator.Estimator(container, role, train_instance_count=1, train_instance_type='ml.c5.xlarge', output_path='s3://bucket/path/output', sagemaker_session=sess) xgboost.set_hyperparameters(max_depth=6, eta=0.3, gamma=0, min_child_weight=1, subsample=1, silent=0, objective="reg:linear", num_round=120) xgboost.fit({'train':'s3://bucket/path/training/data', 'test': 's3://bucket/path/test/data'})
  • 40. © 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved. AmazonSageMaker -XGBoost import sagemaker import boto3 from sagemaker import get_execution_role from sagemaker.amazon.amazon_estimator import get_image_uri sess = sagemaker.Session() role = get_execution_role() container = get_image_uri(boto3.Session().region_name, 'xgboost', '0.90-1') xgboost = sagemaker.estimator.Estimator(container, role, train_instance_count=1, train_instance_type='ml.c5.xlarge', output_path='s3://bucket/path/output', sagemaker_session=sess) xgboost.set_hyperparameters(max_depth=6, eta=0.3, gamma=0, min_child_weight=1, subsample=1, silent=0, objective="reg:linear", num_round=120) xgboost.fit({'train':'s3://bucket/path/training/data', 'test': 's3://bucket/path/test/data'})
  • 41. © 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved. AmazonSageMaker -XGBoost import sagemaker import boto3 from sagemaker import get_execution_role from sagemaker.amazon.amazon_estimator import get_image_uri sess = sagemaker.Session() role = get_execution_role() container = get_image_uri(boto3.Session().region_name, 'xgboost', '0.90-1') xgboost = sagemaker.estimator.Estimator(container, role, train_instance_count=1, train_instance_type='ml.c5.xlarge', output_path='s3://bucket/path/output', sagemaker_session=sess) xgboost.set_hyperparameters(max_depth=6, eta=0.3, gamma=0, min_child_weight=1, subsample=1, silent=0, objective="reg:linear", num_round=120) xgboost.fit({'train':'s3://bucket/path/training/data', 'test': 's3://bucket/path/test/data'})
  • 42. © 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved. AmazonSageMaker -XGBoost import sagemaker import boto3 from sagemaker import get_execution_role from sagemaker.amazon.amazon_estimator import get_image_uri sess = sagemaker.Session() role = get_execution_role() container = get_image_uri(boto3.Session().region_name, 'xgboost', '0.90-1') xgboost = sagemaker.estimator.Estimator(container, role, train_instance_count=1, train_instance_type='ml.c5.xlarge', output_path='s3://bucket/path/output', sagemaker_session=sess) xgboost.set_hyperparameters(max_depth=6, eta=0.3, gamma=0, min_child_weight=1, subsample=1, silent=0, objective="reg:linear", num_round=120) xgboost.fit({'train':'s3://bucket/path/training/data', 'test': 's3://bucket/path/test/data'})
  • 43. © 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved. AmazonSageMaker -XGBoost import sagemaker import boto3 from sagemaker import get_execution_role from sagemaker.amazon.amazon_estimator import get_image_uri sess = sagemaker.Session() role = get_execution_role() container = get_image_uri(boto3.Session().region_name, 'xgboost', '0.90-1') xgboost = sagemaker.estimator.Estimator(container, role, train_instance_count=1, train_instance_type='ml.c5.xlarge', output_path='s3://bucket/path/output', sagemaker_session=sess) xgboost.set_hyperparameters(max_depth=6, eta=0.3, gamma=0, min_child_weight=1, subsample=1, silent=0, objective="reg:linear", num_round=120) xgboost.fit({'train':'s3://bucket/path/training/data', 'test': 's3://bucket/path/test/data'})
  • 44. © 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved. AmazonSageMaker -XGBoost xgboost_predictor = xgboost.deploy(initial_instance_count=1, instance_type='ml.m5.xlarge') from sagemaker.predictor import csv_serializer, json_deserializer xgboost_predictor.content_type = 'text/csv' xgboost_predictor.serializer = csv_serializer xgboost_predictor.deserializer = json_deserializer result = xgboost_predictor.predict(val_df.sample(n=1)) print("prediction: {}".format(result))
  • 45. © 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved. AmazonSageMaker -XGBoost xgboost_predictor = xgboost.deploy(initial_instance_count=1, instance_type='ml.m5.xlarge') from sagemaker.predictor import csv_serializer, json_deserializer xgboost_predictor.content_type = 'text/csv' xgboost_predictor.serializer = csv_serializer xgboost_predictor.deserializer = json_deserializer result = xgboost_predictor.predict(val_df.sample(n=1)) print("prediction: {}".format(result))
  • 46. © 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved. AmazonSageMaker -XGBoost xgboost_predictor = xgboost.deploy(initial_instance_count=1, instance_type='ml.m5.xlarge') from sagemaker.predictor import csv_serializer, json_deserializer xgboost_predictor.content_type = 'text/csv' xgboost_predictor.serializer = csv_serializer xgboost_predictor.deserializer = json_deserializer result = xgboost_predictor.predict(val_df.sample(n=1)) print("prediction: {}".format(result))
  • 47. © 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved. AmazonSageMaker -XGBoost xgboost_predictor = xgboost.deploy(initial_instance_count=1, instance_type='ml.m5.xlarge') from sagemaker.predictor import csv_serializer, json_deserializer xgboost_predictor.content_type = 'text/csv' xgboost_predictor.serializer = csv_serializer xgboost_predictor.deserializer = json_deserializer result = xgboost_predictor.predict(val_df.sample(n=1)) print("prediction: {}".format(result))
  • 48. © 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved. AmazonSageMaker -XGBoost xgboost_predictor = xgboost.deploy(initial_instance_count=1, instance_type='ml.m5.xlarge') from sagemaker.predictor import csv_serializer, json_deserializer xgboost_predictor.content_type = 'text/csv' xgboost_predictor.serializer = csv_serializer xgboost_predictor.deserializer = json_deserializer result = xgboost_predictor.predict(val_df.sample(n=1)) print("prediction: {}".format(result))
  • 49. ¡Gracias! © 2020, Amazon Web Services, Inc. or its affiliates. All rights reserved. Edzon Sánchez edzons@amazon.com

Editor's Notes

  1. Amazon Rekognition Image and Video make it easy to add image and video analysis to your applications. You just provide an image or video to the Rekognition API, and the service can identify the objects, people, text, scenes, and activities, as well as detect any inappropriate content. Amazon Rekognition also provides highly accurate facial analysis and facial recognition, even with live stream video. You can detect, analyze, and compare faces for a wide variety of user verification, cataloging, people counting, and public safety use cases. For example, Marinas Analytics is using Amazon Rekognition to identify, locate, and rescue missing persons. Marinas added facial recognition to Traffic Jam, its suite of tools for law enforcement agencies working on these types of investigations, and has effectively turned facial recognition technology against the vast secret networks of human traffickers.
  2. There is so much data now that's being locked up in audio and video files. The problem is that it’s really hard to search audio well. The best way to do it is to convert it from audio to text. Traditionally, how people have done this is that they've hired manual transcription agencies. Doing so is expensive and time-consuming. So, people typically only pick out the most important things they want to transcribe, and they leave the rest on the table. All this data and all this value is sitting out there, not being taken advantage of and leveraged. Amazon Transcribe solves this problem. Transcribe does long-form automatic speech recognition. It can analyze any WAV or MP3 audio file and return text. It has many uses, including: call logs, subtitles for videos, and capturing what's said in a presentation or a meeting. We started with English and Spanish, but we'll have many more languages coming soon. One of the things that is different from other transcription services is that the text won't display as just one long uninterrupted string of text as with other transcription services. Instead, we use machine learning to add in punctuation and grammatical formatting so the text is immediately usable. Then we time-stamp every word so you can align subtitles to the video to make for indexing purposes. The service supports high-quality audio and, because so much of the audio data today is generated from phones that produce lower-quality, low-bit-rate audio, we uniquely support this as well. Very soon, you’ll also be able to distinguish between multiple speakers, and add your own custom libraries and vocabularies, to manage words that have different meanings. To bring this to life, here are a couple of examples of how Transcribe is working in practice today: In Media & Entertainment Transcribe is used to extract text from rich media as an alternative to closed captioning; Call Centers use Transcribe against phone calls to understand behavior, training opportunities, and call routing.
  3. Our customers’ customers can be located all over the world and speak several different languages. They want to translate content into different languages. Here again, the way that people traditionally solved this problem is that they hired translation agencies that are expensive in terms of time and money. Customers choose only their most important content to translate to manage the costs, and they leave all that value on the table. Amazon Translate, which automatically translates text between languages, helps to solve this problem. Translate is great for use cases that require real-time translation. Examples of this are live customer support and business communications over social media. You can also translate an entire bucket at one time in a batch operation. Soon, our customers will be able to use Translate to recognize the source language on-the-fly, so that they won’t need to specify the language of origin. And, as is the case with our other services, this one is very cost-effective. As an example of how Translate can benefit our customers, the auto-translation capabilities will help them expand their brands globally.  
  4. Amazon Polly provides the ability to develop natural-sounding, accurate, and intelligible speech in 52 voices across 25 languages. These are available globally in 14 AWS regions. The naturalness of the voice is very important, as this is a quality measure and is at the leading edge of where this science can go. If customers are looking for a replacement for their Interactive Voice Response (or IVR) systems or synthetic voices for other applications, it’s a big leap ahead in quality. This is an exciting area for spoken responses. We have two ways for customers to interact with Polly. One is by creating text dynamically and calling a service to have it speak. The other is called caching which is used when you create a scripted output, post it in the cloud, save it to an MP3, and then run the MP3. This is an enormous cost savings if you run these messages repeatedly. Polly provides the foundational level so that you can launch disconnected devices, as well. It enables customers to build all of the instructions into a script and load these inside the device itself with the MP3 onboard, becoming a self-contained system. An example of this is an IoT manufacturer who is building Polly into a security system using Alexa as well. They built dynamic interactive tutorials with voice projecting from the security device. This is an interesting and alternative way of embedding voice at the edge.
  5. Amazon Comprehend is a natural language processing service that uses machine learning to find insights and relationships in text. Amazon Comprehend identifies the language of the text; extracts key phrases, places, people, brands, or events; understands how positive or negative the text is; and automatically organizes a collection of text files by topic.   Our customers are using Amazon Comprehend to identify key topics, entities, and sentiments in social media and news streams, and to enhance their ability to access and aggregate unstructured data from the vast document libraries that exist within their organizations. Hotels.com has thousands of customer views and comments that are submitted by people who stay at the properties. It’s historically been difficult to find what matters in all this data. By using Amazon Comprehend, Hotels.com is able to uncover the unique characteristics that people like or don’t like about each hotel. Consequently, the company is better able to make recommendations to their users.
  6. Amazon Lex uses the automatic speech recognition and natural language understanding technology that fuels Amazon Alexa to allow developers to quickly build intelligent conversational applications, such as chatbots. With Lex, any application running on the web, a mobile app, or a device, can process natural language using an API or SDK. Lex will apply automatic speech recognition (referred to as ASR) and natural language understanding (referred to as NLU) to the incoming message to understand the intent of the user. In turn, this inbound request is mapped to a Lambda function which processes the information, forms a response, and passes it back to the user as either voice, using Polly, or text. Amazon Lex has an integrated development console that allows users to build multi-step conversations that can be tested in the AWS console and then deployed to a custom platform, Facebook Messenger, Slack, Kik, and Twilio. Amazon provides a collection of enterprise connectors for Amazon Lex to Salesforce, Microsoft Dynamics, Marketo, Zendesk, Quickbooks, and HubSpot. These connectors help customers build new interfaces around existing enterprise data. As a fully managed service, Amazon Lex scales automatically, so you don’t need to worry about managing infrastructure.