SlideShare a Scribd company logo
1 of 39
All around
Machine Learning
Tensorflow, ML APIs, Google Assistant
Oksana Savenko
student of Karazin Kharkiv
National University
ML is a world of capabilities
What’s it about?
● Recommendation systems
● Predictions
● Recognition abilities
● Diagnostics
● Anomaly detection
ML in Google
ML in Google
++
Flow of Tensors
Neural Network Classifier
Iris Setosa Iris Versicolor Iris Virginica
Code
8
Deep Playground
TensorFlow Architecture
12
13
14
1.3 <= 1.2
# Read text file
dataset = (tf.contrib.data.TextLineDataset(file_path)
# Skip header row
.skip(1)
# Transform each elem by applying decode_csv fn
.map(decode_csv))
# Randomize input
dataset = dataset.shuffle(buffer_size=256)
# Repeats dataset this # times
dataset = dataset.repeat(repeat_count)
# Batch size to use
dataset = dataset.batch(32)
iterator = dataset.make_one_shot_iterator()
batch_features, batch_labels = iterator.get_next()
# Load dataset
training_set =
tf.contrib.learn.datasets.base.load_csv_with_header(
filename=IRIS_TRAINING,
target_dtype=np.int,
features_dtype=np.float32)
feature_columns =
[tf.feature_column.numeric_column("x", shape=[4])]
# Define the training inputs
train_input_fn = tf.estimator.inputs.numpy_input_fn(
x={"x": np.array(training_set.data)},
y=np.array(training_set.target),
Cloud ML Engine
Google Cloud Machine Learning Use Cases
MNIST
17
MNIST
18
TensorBoard
19
ML APIs
https://cloud.google.com/vision/docs/drag-and-drop
What’s the game?
Translation API
23
Double Kill
Optical Character
Recognition (OCP)
Google Cloud Functions
Google Cloud Pub/Sub
Google Cloud Storage
Google Cloud Translation API
Google Cloud Vision API
# разворачиваем processImage
gcloud beta functions deploy ocr-extract --stage-bucket [YOUR_STAGING_BUCKET_NAME] --trigger-bucket
[YOUR_IMAGE_BUCKET_NAME] --entry-point processImage
# разворачиваем translateText
gcloud beta functions deploy ocr-extract --stage-bucket [YOUR_STAGING_BUCKET_NAME] --trigger-bucket
[YOUR_IMAGE_BUCKET_NAME] --entry-point processImage
# разворачиваем saveResult
gcloud beta functions deploy ocr-save --stage-bucket [YOUR_TEXT_BUCKET_NAME] --trigger-topic
[YOUR_RESULT_TOPIC_NAME] --entry-point saveResult
25
# создаем бакеты для данных
gsutil mb gs://[YOUR_STAGING_BUCKET_NAME]
gsutil mb gs://[YOUR_IMAGE_BUCKET_NAME]
gsutil mb gs://[YOUR_TEXT_BUCKET_NAME]
# локально создаем папку проекта
mkdir ~/gcf_ocr
cd ~/gcf_ocr
# портируем index.js и package.json с Git
# создаем новый файл
config.json
{
"RESULT_TOPIC": "[YOUR_RESULT_TOPIC_NAME]",
"RESULT_BUCKET": "[YOUR_TEXT_BUCKET_NAME]",
"TRANSLATE_TOPIC":
"[YOUR_TRANSLATE_TOPIC_NAME]",
"TRANSLATE": true,
"TO_LANG": ["en", "fr", "es", "ja", "ru"]
}
# загружаем картинку
gsutil cp [PATH_TO_IMAGE] gs://[YOUR_IMAGE_BUCKET_NAME]
# проверяем
gcloud beta functions logs read --limit 100
LEVEL NAME EXECUTION_ID TIME_UTC LOG
D ocr-extract 155750695892074 2017-09-25 18:51:28.260 Function execution started
I ocr-extract 155750695892074 2017-09-25 18:51:28.649 Looking for text in image bender.png
I ocr-extract 155750695892074 2017-09-25 18:51:31.148 Extracted text from image (9 chars)
I ocr-extract 155750695892074 2017-09-25 18:51:31.722 Detected language "en" for bender.png
I ocr-extract 155750695892074 2017-09-25 18:51:32.944 File bender.png processed.
D ocr-extract 155750695892074 2017-09-25 18:51:32.950 Function execution took 4690 ms, finished with status: 'ok'
D ocr-translate 113818010410062 2017-09-25 18:51:34.044 Function execution started
D ocr-save 113818102696070 2017-09-25 18:51:34.276 Function execution started
I ocr-translate 113818010410062 2017-09-25 18:51:34.456 Translating text into ru
I ocr-save 113818102696070 2017-09-25 18:51:34.680 Received request to save file bender.png
I ocr-save 113818102696070 2017-09-25 18:51:34.769 Saving result to bender.png_to_en.txt in bucket txtbuck
I ocr-translate 113818010410062 2017-09-25 18:51:35.921 Text translated to ru
D ocr-translate 113818010410062 2017-09-25 18:51:35.928 Function execution took 1885 ms, finished with status: 'ok'
...
I ocr-save 113817650764455 2017-09-25 18:51:48.919 File saved.
D ocr-save 113817650764455 2017-09-25 18:51:48.967 Function execution took 7642 ms, finished with status: 'ok'
26
APPLAUDISSEMENTS APPLAUSE 拍手 APLAUSOS АПЛОДИСМЕНТЫ
Video Intelligence API BETA
Features
● label detection
● shot change detection
● regionalization
Speech API
I almost understand
Jobs API BETA
● check better job site
engagement
● check higher apply rates
● check increased candidate
conversion
● check freed up product and
engineering resources
Google Assistant
32
2 Ways to integrate
Google Assistant library
Hands-free activation - activate your device by saying Hey
Google or Ok Google, just like with Google Home!
Audio capture and playback
Conversation state management
Timer and alarm management
Google Assistant gRPС API
Idiomatic client libraries in 10 languages
Highly efficient on wire and with a simple service definition
framework
Bi-directional streaming with http/2 based transport
Pluggable auth, tracing, load balancing and health
checking
Google Assistant gRPC API
Conversation Design
Create a persona
Pick up the voice
Tricks
● Unlock Your Phone with Google
Assistant
● Get Google Assistant to Remember
Things
● Take a Selfie
● See Your Photos
● Post to Facebook by Voice
● Translate on the Go
https://ifttt.com/join
35
36
Google News
наушники Pixel Buds
37
Google News
Teachable Machine https://teachablemachine.withgoogle.com/
38
Oksana Savenko
facebook.com/gingertailed
Q&A
39

More Related Content

What's hot

The Weather of the Century Part 2: High Performance
The Weather of the Century Part 2: High PerformanceThe Weather of the Century Part 2: High Performance
The Weather of the Century Part 2: High Performance
MongoDB
 
XSpect, a lightweight library to make your code reusable and maintainable.
XSpect, a lightweight library to make your code reusable and maintainable.XSpect, a lightweight library to make your code reusable and maintainable.
XSpect, a lightweight library to make your code reusable and maintainable.
岡諭 李
 

What's hot (20)

The Ring programming language version 1.10 book - Part 10 of 212
The Ring programming language version 1.10 book - Part 10 of 212The Ring programming language version 1.10 book - Part 10 of 212
The Ring programming language version 1.10 book - Part 10 of 212
 
Python database interfaces
Python database  interfacesPython database  interfaces
Python database interfaces
 
Apex code benchmarking
Apex code benchmarkingApex code benchmarking
Apex code benchmarking
 
Scheduling in Linux and Web Servers
Scheduling in Linux and Web ServersScheduling in Linux and Web Servers
Scheduling in Linux and Web Servers
 
Ac cuda c_5
Ac cuda c_5Ac cuda c_5
Ac cuda c_5
 
Accelerating Local Search with PostgreSQL (KNN-Search)
Accelerating Local Search with PostgreSQL (KNN-Search)Accelerating Local Search with PostgreSQL (KNN-Search)
Accelerating Local Search with PostgreSQL (KNN-Search)
 
Weather of the Century: Visualization
Weather of the Century: VisualizationWeather of the Century: Visualization
Weather of the Century: Visualization
 
Ac cuda c_4
Ac cuda c_4Ac cuda c_4
Ac cuda c_4
 
orca_fosdem_FINAL
orca_fosdem_FINALorca_fosdem_FINAL
orca_fosdem_FINAL
 
Weather of the Century: Design and Performance
Weather of the Century: Design and PerformanceWeather of the Century: Design and Performance
Weather of the Century: Design and Performance
 
The Weather of the Century
The Weather of the CenturyThe Weather of the Century
The Weather of the Century
 
The Weather of the Century Part 3: Visualization
The Weather of the Century Part 3: VisualizationThe Weather of the Century Part 3: Visualization
The Weather of the Century Part 3: Visualization
 
Relational Database Access with Python
Relational Database Access with PythonRelational Database Access with Python
Relational Database Access with Python
 
Handout3o
Handout3oHandout3o
Handout3o
 
Tailored source-code-transformation-synthesize-computationally-diverse-progra...
Tailored source-code-transformation-synthesize-computationally-diverse-progra...Tailored source-code-transformation-synthesize-computationally-diverse-progra...
Tailored source-code-transformation-synthesize-computationally-diverse-progra...
 
Automation in angular js
Automation in angular jsAutomation in angular js
Automation in angular js
 
The Ring programming language version 1.9 book - Part 9 of 210
The Ring programming language version 1.9 book - Part 9 of 210The Ring programming language version 1.9 book - Part 9 of 210
The Ring programming language version 1.9 book - Part 9 of 210
 
The Weather of the Century Part 2: High Performance
The Weather of the Century Part 2: High PerformanceThe Weather of the Century Part 2: High Performance
The Weather of the Century Part 2: High Performance
 
Virtual Memory (Making a Process)
Virtual Memory (Making a Process)Virtual Memory (Making a Process)
Virtual Memory (Making a Process)
 
XSpect, a lightweight library to make your code reusable and maintainable.
XSpect, a lightweight library to make your code reusable and maintainable.XSpect, a lightweight library to make your code reusable and maintainable.
XSpect, a lightweight library to make your code reusable and maintainable.
 

Similar to Al around ML 2017, Оксана Савенко, студентка НТУ имени Каразина

Spca2014 advanced share point troubleshooting hessing
Spca2014 advanced share point troubleshooting hessingSpca2014 advanced share point troubleshooting hessing
Spca2014 advanced share point troubleshooting hessing
NCCOMMS
 

Similar to Al around ML 2017, Оксана Савенко, студентка НТУ имени Каразина (20)

Workshop "Can my .NET application use less CPU / RAM?", Yevhen Tatarynov
Workshop "Can my .NET application use less CPU / RAM?", Yevhen TatarynovWorkshop "Can my .NET application use less CPU / RAM?", Yevhen Tatarynov
Workshop "Can my .NET application use less CPU / RAM?", Yevhen Tatarynov
 
Yevhen Tatarynov "From POC to High-Performance .NET applications"
Yevhen Tatarynov "From POC to High-Performance .NET applications"Yevhen Tatarynov "From POC to High-Performance .NET applications"
Yevhen Tatarynov "From POC to High-Performance .NET applications"
 
Kerberizing Spark: Spark Summit East talk by Abel Rincon and Jorge Lopez-Malla
Kerberizing Spark: Spark Summit East talk by Abel Rincon and Jorge Lopez-MallaKerberizing Spark: Spark Summit East talk by Abel Rincon and Jorge Lopez-Malla
Kerberizing Spark: Spark Summit East talk by Abel Rincon and Jorge Lopez-Malla
 
Apache Cassandra at Macys
Apache Cassandra at MacysApache Cassandra at Macys
Apache Cassandra at Macys
 
How to create Treasure Data #dotsbigdata
How to create Treasure Data #dotsbigdataHow to create Treasure Data #dotsbigdata
How to create Treasure Data #dotsbigdata
 
Project Tungsten: Bringing Spark Closer to Bare Metal
Project Tungsten: Bringing Spark Closer to Bare MetalProject Tungsten: Bringing Spark Closer to Bare Metal
Project Tungsten: Bringing Spark Closer to Bare Metal
 
Certification Study Group -Professional ML Engineer Session 2 (GCP-TensorFlow...
Certification Study Group -Professional ML Engineer Session 2 (GCP-TensorFlow...Certification Study Group -Professional ML Engineer Session 2 (GCP-TensorFlow...
Certification Study Group -Professional ML Engineer Session 2 (GCP-TensorFlow...
 
Big Data Tools in AWS
Big Data Tools in AWSBig Data Tools in AWS
Big Data Tools in AWS
 
Scaling 100PB Data Warehouse in Cloud
Scaling 100PB Data Warehouse in CloudScaling 100PB Data Warehouse in Cloud
Scaling 100PB Data Warehouse in Cloud
 
Build a DataWarehouse for your logs with Python, AWS Athena and Glue
Build a DataWarehouse for your logs with Python, AWS Athena and GlueBuild a DataWarehouse for your logs with Python, AWS Athena and Glue
Build a DataWarehouse for your logs with Python, AWS Athena and Glue
 
JDD2015: Make your world event driven - Krzysztof Dębski
JDD2015: Make your world event driven - Krzysztof DębskiJDD2015: Make your world event driven - Krzysztof Dębski
JDD2015: Make your world event driven - Krzysztof Dębski
 
Beyond php - it's not (just) about the code
Beyond php - it's not (just) about the codeBeyond php - it's not (just) about the code
Beyond php - it's not (just) about the code
 
Lessons Learned While Scaling Elasticsearch at Vinted
Lessons Learned While Scaling Elasticsearch at VintedLessons Learned While Scaling Elasticsearch at Vinted
Lessons Learned While Scaling Elasticsearch at Vinted
 
Beyond php it's not (just) about the code
Beyond php   it's not (just) about the codeBeyond php   it's not (just) about the code
Beyond php it's not (just) about the code
 
Treasure Data and AWS - Developers.io 2015
Treasure Data and AWS - Developers.io 2015Treasure Data and AWS - Developers.io 2015
Treasure Data and AWS - Developers.io 2015
 
The Flow of TensorFlow
The Flow of TensorFlowThe Flow of TensorFlow
The Flow of TensorFlow
 
Spca2014 advanced share point troubleshooting hessing
Spca2014 advanced share point troubleshooting hessingSpca2014 advanced share point troubleshooting hessing
Spca2014 advanced share point troubleshooting hessing
 
Xephon K A Time series database with multiple backends
Xephon K A Time series database with multiple backendsXephon K A Time series database with multiple backends
Xephon K A Time series database with multiple backends
 
More Data, More Problems: Evolving big data machine learning pipelines with S...
More Data, More Problems: Evolving big data machine learning pipelines with S...More Data, More Problems: Evolving big data machine learning pipelines with S...
More Data, More Problems: Evolving big data machine learning pipelines with S...
 
Recipe 14 of Data Warehouse and Business Intelligence - Build a Staging Area ...
Recipe 14 of Data Warehouse and Business Intelligence - Build a Staging Area ...Recipe 14 of Data Warehouse and Business Intelligence - Build a Staging Area ...
Recipe 14 of Data Warehouse and Business Intelligence - Build a Staging Area ...
 

More from Alina Vilk

Architecture components, Константин Марс, TeamLead, Senior Developer, DataArt
Architecture components, Константин Марс, TeamLead, Senior Developer, DataArtArchitecture components, Константин Марс, TeamLead, Senior Developer, DataArt
Architecture components, Константин Марс, TeamLead, Senior Developer, DataArt
Alina Vilk
 
Кирилл Безпалый, .NET Developer, Ciklum
Кирилл Безпалый, .NET Developer, CiklumКирилл Безпалый, .NET Developer, Ciklum
Кирилл Безпалый, .NET Developer, Ciklum
Alina Vilk
 
Александр Сергиенко, Senior Android Developer, DataArt
Александр Сергиенко, Senior Android Developer, DataArtАлександр Сергиенко, Senior Android Developer, DataArt
Александр Сергиенко, Senior Android Developer, DataArt
Alina Vilk
 

More from Alina Vilk (20)

Designer in you, Irina Shapoval, Lead Designer, DataArt
Designer in you, Irina Shapoval, Lead Designer, DataArtDesigner in you, Irina Shapoval, Lead Designer, DataArt
Designer in you, Irina Shapoval, Lead Designer, DataArt
 
.NET framework vs .net core 3.1 commons &amp; differences
 .NET framework vs .net core 3.1  commons &amp; differences .NET framework vs .net core 3.1  commons &amp; differences
.NET framework vs .net core 3.1 commons &amp; differences
 
Expression trees in c#, Алексей Голубь (Svitla Systems)
Expression trees in c#, Алексей Голубь (Svitla Systems)Expression trees in c#, Алексей Голубь (Svitla Systems)
Expression trees in c#, Алексей Голубь (Svitla Systems)
 
"Dev to PM" D.Fedotov
"Dev to PM" D.Fedotov"Dev to PM" D.Fedotov
"Dev to PM" D.Fedotov
 
Игорь Литвиненко (Senior iOS- и Android-разработчик,DataArt)
Игорь Литвиненко (Senior iOS- и Android-разработчик,DataArt)Игорь Литвиненко (Senior iOS- и Android-разработчик,DataArt)
Игорь Литвиненко (Senior iOS- и Android-разработчик,DataArt)
 
Алексей Рыбаков (Senior Engineer,Technical Evangelist DataArt )
Алексей Рыбаков (Senior Engineer,Technical Evangelist DataArt ) Алексей Рыбаков (Senior Engineer,Technical Evangelist DataArt )
Алексей Рыбаков (Senior Engineer,Technical Evangelist DataArt )
 
Ирина Шаповал,(Lead UI/UX дизайнер, DataArt)
Ирина Шаповал,(Lead UI/UX дизайнер, DataArt)Ирина Шаповал,(Lead UI/UX дизайнер, DataArt)
Ирина Шаповал,(Lead UI/UX дизайнер, DataArt)
 
Devops, v.02, Alexander Pavlenko (DataArt)
Devops, v.02, Alexander Pavlenko (DataArt)Devops, v.02, Alexander Pavlenko (DataArt)
Devops, v.02, Alexander Pavlenko (DataArt)
 
O DevOps, Stanislav Kolenkin ( DataArt)
O DevOps, Stanislav Kolenkin ( DataArt)O DevOps, Stanislav Kolenkin ( DataArt)
O DevOps, Stanislav Kolenkin ( DataArt)
 
Interactive 3D graphics for web with three.js, Andrey Vedilin, DataArt
Interactive  3D graphics for web with three.js, Andrey Vedilin, DataArtInteractive  3D graphics for web with three.js, Andrey Vedilin, DataArt
Interactive 3D graphics for web with three.js, Andrey Vedilin, DataArt
 
Architecture components, Константин Марс, TeamLead, Senior Developer, DataArt
Architecture components, Константин Марс, TeamLead, Senior Developer, DataArtArchitecture components, Константин Марс, TeamLead, Senior Developer, DataArt
Architecture components, Константин Марс, TeamLead, Senior Developer, DataArt
 
Встреча Google Post IO ( Владимир Иванов, Катерина Заворотченко и Сергей Комлач)
Встреча Google Post IO ( Владимир Иванов, Катерина Заворотченко и Сергей Комлач)Встреча Google Post IO ( Владимир Иванов, Катерина Заворотченко и Сергей Комлач)
Встреча Google Post IO ( Владимир Иванов, Катерина Заворотченко и Сергей Комлач)
 
Кирилл Безпалый, .NET Developer, Ciklum
Кирилл Безпалый, .NET Developer, CiklumКирилл Безпалый, .NET Developer, Ciklum
Кирилл Безпалый, .NET Developer, Ciklum
 
Игорь Леонтьев, Lead Architect on all Blockchain projects of Viseo group
Игорь Леонтьев, Lead Architect on all Blockchain projects of Viseo groupИгорь Леонтьев, Lead Architect on all Blockchain projects of Viseo group
Игорь Леонтьев, Lead Architect on all Blockchain projects of Viseo group
 
Александр Сергиенко, Senior Android Developer, DataArt
Александр Сергиенко, Senior Android Developer, DataArtАлександр Сергиенко, Senior Android Developer, DataArt
Александр Сергиенко, Senior Android Developer, DataArt
 
Евгений Дубовик, Senior Developer, DataArtDb presentation gdg
Евгений Дубовик, Senior Developer, DataArtDb presentation gdgЕвгений Дубовик, Senior Developer, DataArtDb presentation gdg
Евгений Дубовик, Senior Developer, DataArtDb presentation gdg
 
Дмитрий Козицкий,Lead UX / UI Designer, DataArt
Дмитрий Козицкий,Lead UX / UI Designer, DataArtДмитрий Козицкий,Lead UX / UI Designer, DataArt
Дмитрий Козицкий,Lead UX / UI Designer, DataArt
 
Игорь Юзовицкий,UX Expert, DataArt
Игорь Юзовицкий,UX Expert, DataArtИгорь Юзовицкий,UX Expert, DataArt
Игорь Юзовицкий,UX Expert, DataArt
 
Android Things, Alexey Rybakov, Technical Evangelist, DataArt
Android Things, Alexey Rybakov, Technical Evangelist, DataArtAndroid Things, Alexey Rybakov, Technical Evangelist, DataArt
Android Things, Alexey Rybakov, Technical Evangelist, DataArt
 
«Делегирование как идеальный способ угробить проект», Александр Ивахненко, IT...
«Делегирование как идеальный способ угробить проект», Александр Ивахненко, IT...«Делегирование как идеальный способ угробить проект», Александр Ивахненко, IT...
«Делегирование как идеальный способ угробить проект», Александр Ивахненко, IT...
 

Recently uploaded

The basics of sentences session 3pptx.pptx
The basics of sentences session 3pptx.pptxThe basics of sentences session 3pptx.pptx
The basics of sentences session 3pptx.pptx
heathfieldcps1
 

Recently uploaded (20)

Interdisciplinary_Insights_Data_Collection_Methods.pptx
Interdisciplinary_Insights_Data_Collection_Methods.pptxInterdisciplinary_Insights_Data_Collection_Methods.pptx
Interdisciplinary_Insights_Data_Collection_Methods.pptx
 
Application orientated numerical on hev.ppt
Application orientated numerical on hev.pptApplication orientated numerical on hev.ppt
Application orientated numerical on hev.ppt
 
Python Notes for mca i year students osmania university.docx
Python Notes for mca i year students osmania university.docxPython Notes for mca i year students osmania university.docx
Python Notes for mca i year students osmania university.docx
 
Google Gemini An AI Revolution in Education.pptx
Google Gemini An AI Revolution in Education.pptxGoogle Gemini An AI Revolution in Education.pptx
Google Gemini An AI Revolution in Education.pptx
 
Accessible Digital Futures project (20/03/2024)
Accessible Digital Futures project (20/03/2024)Accessible Digital Futures project (20/03/2024)
Accessible Digital Futures project (20/03/2024)
 
HMCS Max Bernays Pre-Deployment Brief (May 2024).pptx
HMCS Max Bernays Pre-Deployment Brief (May 2024).pptxHMCS Max Bernays Pre-Deployment Brief (May 2024).pptx
HMCS Max Bernays Pre-Deployment Brief (May 2024).pptx
 
ICT Role in 21st Century Education & its Challenges.pptx
ICT Role in 21st Century Education & its Challenges.pptxICT Role in 21st Century Education & its Challenges.pptx
ICT Role in 21st Century Education & its Challenges.pptx
 
Jamworks pilot and AI at Jisc (20/03/2024)
Jamworks pilot and AI at Jisc (20/03/2024)Jamworks pilot and AI at Jisc (20/03/2024)
Jamworks pilot and AI at Jisc (20/03/2024)
 
Micro-Scholarship, What it is, How can it help me.pdf
Micro-Scholarship, What it is, How can it help me.pdfMicro-Scholarship, What it is, How can it help me.pdf
Micro-Scholarship, What it is, How can it help me.pdf
 
Basic Civil Engineering first year Notes- Chapter 4 Building.pptx
Basic Civil Engineering first year Notes- Chapter 4 Building.pptxBasic Civil Engineering first year Notes- Chapter 4 Building.pptx
Basic Civil Engineering first year Notes- Chapter 4 Building.pptx
 
Mehran University Newsletter Vol-X, Issue-I, 2024
Mehran University Newsletter Vol-X, Issue-I, 2024Mehran University Newsletter Vol-X, Issue-I, 2024
Mehran University Newsletter Vol-X, Issue-I, 2024
 
How to Give a Domain for a Field in Odoo 17
How to Give a Domain for a Field in Odoo 17How to Give a Domain for a Field in Odoo 17
How to Give a Domain for a Field in Odoo 17
 
This PowerPoint helps students to consider the concept of infinity.
This PowerPoint helps students to consider the concept of infinity.This PowerPoint helps students to consider the concept of infinity.
This PowerPoint helps students to consider the concept of infinity.
 
SOC 101 Demonstration of Learning Presentation
SOC 101 Demonstration of Learning PresentationSOC 101 Demonstration of Learning Presentation
SOC 101 Demonstration of Learning Presentation
 
The basics of sentences session 3pptx.pptx
The basics of sentences session 3pptx.pptxThe basics of sentences session 3pptx.pptx
The basics of sentences session 3pptx.pptx
 
How to Manage Global Discount in Odoo 17 POS
How to Manage Global Discount in Odoo 17 POSHow to Manage Global Discount in Odoo 17 POS
How to Manage Global Discount in Odoo 17 POS
 
Fostering Friendships - Enhancing Social Bonds in the Classroom
Fostering Friendships - Enhancing Social Bonds  in the ClassroomFostering Friendships - Enhancing Social Bonds  in the Classroom
Fostering Friendships - Enhancing Social Bonds in the Classroom
 
ICT role in 21st century education and it's challenges.
ICT role in 21st century education and it's challenges.ICT role in 21st century education and it's challenges.
ICT role in 21st century education and it's challenges.
 
Plant propagation: Sexual and Asexual propapagation.pptx
Plant propagation: Sexual and Asexual propapagation.pptxPlant propagation: Sexual and Asexual propapagation.pptx
Plant propagation: Sexual and Asexual propapagation.pptx
 
2024-NATIONAL-LEARNING-CAMP-AND-OTHER.pptx
2024-NATIONAL-LEARNING-CAMP-AND-OTHER.pptx2024-NATIONAL-LEARNING-CAMP-AND-OTHER.pptx
2024-NATIONAL-LEARNING-CAMP-AND-OTHER.pptx
 

Al around ML 2017, Оксана Савенко, студентка НТУ имени Каразина

  • 1. All around Machine Learning Tensorflow, ML APIs, Google Assistant Oksana Savenko student of Karazin Kharkiv National University ML is a world of capabilities
  • 2. What’s it about? ● Recommendation systems ● Predictions ● Recognition abilities ● Diagnostics ● Anomaly detection
  • 5. ++
  • 7. Neural Network Classifier Iris Setosa Iris Versicolor Iris Virginica
  • 9.
  • 10.
  • 13. 13
  • 14. 14 1.3 <= 1.2 # Read text file dataset = (tf.contrib.data.TextLineDataset(file_path) # Skip header row .skip(1) # Transform each elem by applying decode_csv fn .map(decode_csv)) # Randomize input dataset = dataset.shuffle(buffer_size=256) # Repeats dataset this # times dataset = dataset.repeat(repeat_count) # Batch size to use dataset = dataset.batch(32) iterator = dataset.make_one_shot_iterator() batch_features, batch_labels = iterator.get_next() # Load dataset training_set = tf.contrib.learn.datasets.base.load_csv_with_header( filename=IRIS_TRAINING, target_dtype=np.int, features_dtype=np.float32) feature_columns = [tf.feature_column.numeric_column("x", shape=[4])] # Define the training inputs train_input_fn = tf.estimator.inputs.numpy_input_fn( x={"x": np.array(training_set.data)}, y=np.array(training_set.target),
  • 16. Google Cloud Machine Learning Use Cases
  • 21.
  • 24. Double Kill Optical Character Recognition (OCP) Google Cloud Functions Google Cloud Pub/Sub Google Cloud Storage Google Cloud Translation API Google Cloud Vision API
  • 25. # разворачиваем processImage gcloud beta functions deploy ocr-extract --stage-bucket [YOUR_STAGING_BUCKET_NAME] --trigger-bucket [YOUR_IMAGE_BUCKET_NAME] --entry-point processImage # разворачиваем translateText gcloud beta functions deploy ocr-extract --stage-bucket [YOUR_STAGING_BUCKET_NAME] --trigger-bucket [YOUR_IMAGE_BUCKET_NAME] --entry-point processImage # разворачиваем saveResult gcloud beta functions deploy ocr-save --stage-bucket [YOUR_TEXT_BUCKET_NAME] --trigger-topic [YOUR_RESULT_TOPIC_NAME] --entry-point saveResult 25 # создаем бакеты для данных gsutil mb gs://[YOUR_STAGING_BUCKET_NAME] gsutil mb gs://[YOUR_IMAGE_BUCKET_NAME] gsutil mb gs://[YOUR_TEXT_BUCKET_NAME] # локально создаем папку проекта mkdir ~/gcf_ocr cd ~/gcf_ocr # портируем index.js и package.json с Git # создаем новый файл config.json { "RESULT_TOPIC": "[YOUR_RESULT_TOPIC_NAME]", "RESULT_BUCKET": "[YOUR_TEXT_BUCKET_NAME]", "TRANSLATE_TOPIC": "[YOUR_TRANSLATE_TOPIC_NAME]", "TRANSLATE": true, "TO_LANG": ["en", "fr", "es", "ja", "ru"] } # загружаем картинку gsutil cp [PATH_TO_IMAGE] gs://[YOUR_IMAGE_BUCKET_NAME] # проверяем gcloud beta functions logs read --limit 100 LEVEL NAME EXECUTION_ID TIME_UTC LOG D ocr-extract 155750695892074 2017-09-25 18:51:28.260 Function execution started I ocr-extract 155750695892074 2017-09-25 18:51:28.649 Looking for text in image bender.png I ocr-extract 155750695892074 2017-09-25 18:51:31.148 Extracted text from image (9 chars) I ocr-extract 155750695892074 2017-09-25 18:51:31.722 Detected language "en" for bender.png I ocr-extract 155750695892074 2017-09-25 18:51:32.944 File bender.png processed. D ocr-extract 155750695892074 2017-09-25 18:51:32.950 Function execution took 4690 ms, finished with status: 'ok' D ocr-translate 113818010410062 2017-09-25 18:51:34.044 Function execution started D ocr-save 113818102696070 2017-09-25 18:51:34.276 Function execution started I ocr-translate 113818010410062 2017-09-25 18:51:34.456 Translating text into ru I ocr-save 113818102696070 2017-09-25 18:51:34.680 Received request to save file bender.png I ocr-save 113818102696070 2017-09-25 18:51:34.769 Saving result to bender.png_to_en.txt in bucket txtbuck I ocr-translate 113818010410062 2017-09-25 18:51:35.921 Text translated to ru D ocr-translate 113818010410062 2017-09-25 18:51:35.928 Function execution took 1885 ms, finished with status: 'ok' ... I ocr-save 113817650764455 2017-09-25 18:51:48.919 File saved. D ocr-save 113817650764455 2017-09-25 18:51:48.967 Function execution took 7642 ms, finished with status: 'ok'
  • 26. 26 APPLAUDISSEMENTS APPLAUSE 拍手 APLAUSOS АПЛОДИСМЕНТЫ
  • 27. Video Intelligence API BETA Features ● label detection ● shot change detection ● regionalization
  • 29.
  • 31. Jobs API BETA ● check better job site engagement ● check higher apply rates ● check increased candidate conversion ● check freed up product and engineering resources
  • 33. 2 Ways to integrate Google Assistant library Hands-free activation - activate your device by saying Hey Google or Ok Google, just like with Google Home! Audio capture and playback Conversation state management Timer and alarm management Google Assistant gRPС API Idiomatic client libraries in 10 languages Highly efficient on wire and with a simple service definition framework Bi-directional streaming with http/2 based transport Pluggable auth, tracing, load balancing and health checking Google Assistant gRPC API
  • 34. Conversation Design Create a persona Pick up the voice
  • 35. Tricks ● Unlock Your Phone with Google Assistant ● Get Google Assistant to Remember Things ● Take a Selfie ● See Your Photos ● Post to Facebook by Voice ● Translate on the Go https://ifttt.com/join 35
  • 37. 37 Google News Teachable Machine https://teachablemachine.withgoogle.com/
  • 38. 38