This document provides an overview of different ways to get started with machine learning, from using cloud APIs to developing custom models. It discusses: 1. Using cloud-based APIs for tasks like computer vision, natural language processing and speech recognition which provide pre-trained models with less effort. 2. Using existing model architectures and retraining or fine-tuning them on your own dataset, requiring more work than cloud APIs but less than developing custom models. 3. Developing your own machine learning models for new problems, which is the most flexible but requires the most effort.

1. How To Get Started with
Machine Learning?

2. How Can You Get Started with Machine Learning?
Three ways, with varying complexity:
(1) Use a Cloud-based or Mobile API (Vision, Natural Language,
etc.)
(2) Use an existing model architecture, and retrain it or fine tune
on your dataset
(3) Develop your own machine learning models for new
problems
More
flexible,
but more
effort
required

3. Cloud Machine Learning APIs
See, Hear and Understand the world

4. Cloud
Natural Language
Cloud
Speech
Cloud
Translat
e
Cloud
Vision

5. Faces
Faces, facial landmarks, emotions
OCR
Read and extract text, with
support for > 10 languages
Label
Detect entities from furniture to
transportation
Logos
Identify product logos
Landmarks & Image Properties
Detect landmarks & dominant
color of image
Safe Search
Detect explicit content - adult,
violent, medical and spoof
Cloud Vision API

6. API Usage: Detect Objects in an Image
Image Detected
Items
Vision API
Create JSON
request with the
image or pointer
to an image
Process
the JSON
response
Call the
REST API1 2 3

7. Confidential & ProprietaryGoogle Cloud Platform 7
Cloud Natural Language API
Extract sentence, identify parts of
speech and create dependency parse
trees for each sentence.
Identify entities and label by types such
as person, organization, location, events,
products and media.
Understand the overall sentiment of a
block of text.
Syntax Analysis Entity Recognition
Sentiment Analysis

8. Confidential & ProprietaryGoogle Cloud Platform 8
Cloud Speech API
Automatic Speech Recognition
(ASR) powered by deep learning
neural networking to power your
applications like voice search or
speech transcription.
Recognizes over 80
languages and variants
with an extensive
vocabulary.
Returns partial
recognition results
immediately, as they
become available.
Filter inappropriate
content in text results.
Audio input can be captured by an application’s
microphone or sent from a pre-recorded audio
file. Multiple audio file formats are supported,
including FLAC, AMR, PCMU and linear-16.
Handles noisy audio from many
environments without requiring
additional noise cancellation.
Audio files can be uploaded in the
request and, in future releases,
integrated with Google Cloud
Storage.
Automatic Speech Recognition Global Vocabulary Inappropriate Content
Filtering
Streaming Recognition
Real-time or Buffered Audio Support Noisy Audio Handling Integrated API

9. Mobile Vision API
Providing on-device vision for applications

10. Face API
faces, facial landmarks,
eyes open, smiling
Barcode API
1D and 2D barcodes
Text API
Latin-based text / structure
Common Mobile Vision API
Support for fast image and video on-device detection and tracking.

11. Easy to use Java API
image detected
items
Detector
1.Create a detector object
2.detectedItems = detector.detect(image)
Photo credit developers.google.com/vision

12. Text Structure
Blocks
Lines
Words
Lines
Words Words Words

13. Barcode Detection
1D barcodes
EAN-13/8
UPC-A/E
Code-39/93/128
ITF
Codabar
2D barcodes
QR Code
Data Matrix
PDF-417
AZTEC
UPC
DataMatrix
QR Code
PDF 417

14. Combined Vision & Translation

15. ● Open source Machine
Learning library
● Especially useful for
Deep Learning
● For research and
production
● Apache 2.0 license

16. What we see What the computer “sees”

18. 1818
TensorFlow Playground Demo

19. Complete code
import tensorflow as tf
mnist = tf.contrib.learn.datasets.load_dataset('mnist')
classifier = tf.learn.LinearClassifier(n_classes=10)
classifier.fit(mnist.train.images, mnist.train.labels)
score = metrics.accuracy_score(mnist.test.labels,
classifier.predict(mnist.test.images))
print('Accuracy: {0:f}'.format(score))

20. Complete code
import tensorflow as tf
mnist = tf.contrib.learn.datasets.load_dataset('mnist')
classifier = tf.learn.LinearClassifier(n_classes=10)
classifier.fit(mnist.train.images, mnist.train.labels)
score = metrics.accuracy_score(mnist.test.labels,
classifier.predict(mnist.test.images))
print('Accuracy: {0:f}'.format(score))

21. A little more TensorFlow

22. A multidimensional array.
A graph of operations.

23. Data Flow Graphs
Computation is defined as a directed acyclic graph
(DAG) to optimize an objective function
● Graph is defined in high-level language (Python)
● Graph is compiled and optimized
● Graph is executed (in parts or fully) on available low
level devices (CPU, GPU)
● Data (tensors) flow through the graph
● TensorFlow can compute gradients automatically

24. Architecture
● Core in C++
● Different front ends
○ Python and C++ today, community may add more
Core TensorFlow Execution System
CPU GPU Android iOS ...
C++ front end Python front end ...

25. Raspberry
Pi
DatacentersYour laptop Android iOS
Portable & Scalable

26. /Serving
Open-source solution for serving trained models

27. Examples of Machine Learning

28. http://googleresearch.blogspot.com/2016/05/announcing-syntaxnet-worlds-most.html

30. Questions?