3. What we’ll cover
What is Neural Network and Deep Learning
Machine Learning use cases at Google services
Externalizing the power with ML APIs
TensorFlow: the open source library for ML
TensorFlow in the Wild
Distributed training and prediction with Cloud ML
23. We need to go deeper neural network
From: Convolutional Deep Belief Networks for Scalable Unsupervised Learning of Hierarchical Representations, Honglak Lee et al.
24. From: mNeuron: A Matlab Plugin to Visualize Neurons from Deep Models, Donglai Wei et. al.
27. 27
signal
for Search ranking,
out of hundreds
improvement
to ranking quality
in 2+ years
#3 #1
Search
machine learning for search engines
RankBrain: a deep neural network for search ranking
36. TensorFlow Cloud Machine Learning ML API
Easy-to-Use, for non-ML engineers
Customizable, for Data Scientists
Machine Learning products from Google
37. Image analysis with pre-trained models
No Machine Learning skill required
REST API: receives an image and returns a JSON
$1.50 per 1,000 units
GA - cloud.google.com/vision
Cloud Vision API
38. Confidential & ProprietaryGoogle Cloud Platform 38
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
40. Pre-trained models. No ML skill required
REST API: receives audio and returns texts
Supports 80+ languages
Streaming or non-streaming
Public Beta - cloud.google.com/speech
Cloud Speech API
41. Confidential & ProprietaryGoogle Cloud Platform 41
Features
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
43. Pre-trained models. No ML skill required
REST API: receives text and returns analysis results
Supports English, Spanish and Japanese
GA - cloud.google.com/natural-language
Cloud Natural Language API
44. Confidential & ProprietaryGoogle Cloud Platform 44
Features
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
46. Pre-trained models. No ML skill required
REST API: receives text and returns translated text
8 languages: English to Chinese, French, German,
Japanese, Korean, Portuguese, Spanish, Turkish
Public Beta - cloud.google.com/translate
Cloud Translation API Premium
49. Google's open source library for
machine intelligence
tensorflow.org launched in Nov 2015
Used by many production ML projects
What is TensorFlow?
50. 50
Sharing our tools with researchers and developers
around the world
repository
for “machine learning”
category on GitHub
#1
Released in Nov.
2015
From: http://deliprao.com/archives/168
51. 51
Before
Hire Data Scientists
↓
Understand the math model
↓
Impl with programming code
↓
Train with single GPU
↓
Build a GPU cluster
↓
Train with the GPU cluster
↓
Build a prediction server
or Impl mobile/IoT prediction
After
Easy network design and impl
↓
Train with single machine
↓
Train on the cloud
↓
Prediction on the cloud
or mobile/IoT devices
many people
stuck here
52. # define the network
import tensorflow as tf
x = tf.placeholder(tf.float32, [None, 784])
W = tf.Variable(tf.zeros([784, 10]))
b = tf.Variable(tf.zeros([10]))
y = tf.nn.softmax(tf.matmul(x, W) + b)
# define a training step
y_ = tf.placeholder(tf.float32, [None, 10])
xent = -tf.reduce_sum(y_*tf.log(y))
step =
tf.train.GradientDescentOptimizer(0.01).minimize(xent)
68. The Challenge: Computing Power
DNN requires large training datasets
Large models doesn't fit into a GPU
Requires try-and-errors to find the
best design, configs and params
↓
Need to spend a few days or
weeks to finish a training
69. GPUs run at nanoseconds
GPU cluster needs microsec network
76. Distributed Training with TensorFlow
on Google Cloud
"Large Scale Distributed Systems for Training Neural
Networks", NIPS 2015
Inception / ImageNet: 40x with 50 GPUs
RankBrain: 300x with 500 nodes
77. Fully managed distributed training and prediction
Supports custom TensorFlow graphs
HyperTune for hyper-parameter tuning automation
Integrated with Cloud Dataflow and Cloud Datalab
Public Beta - cloud.google.com/ml
Cloud Machine Learning (Cloud ML)
78. Cloud ML at Work: AUCNET
The largest real-time car auction service in Japan
For 30K used car dealers
The auction volume overs $3.7B every year
Problem: auction entry is time consuming task for dealers
Classifying parts of car for thousands of photos
Identifying the exact car model
79. Solution: Custom Image Classification with TensorFlow/Cloud ML
Used 5,000 training images for 500 car models
Inception v3 + Transfer Learning
Cloud ML: increased training performance for 6x faster
80. Predicting "large loss" cases in car insurance
Old method (Random Forest): 38% accuracy
New method (TensorFlow): 73% accuracy
A Global Insurance Firm
82. 8282
Ready to use Machine
Learning models
Use your own data to
train models
Cloud
Vision API
Cloud
Speech API
Cloud
Translation API
Cloud Machine Learning
Develop - Model - Test
Google
BigQuery
Cloud
Storage
Cloud
Datalab
Beta
GA BetaGA
Beta
GA
GA GA
Cloud Natural
Language API
83. Tensor Processing Unit
ASIC for TensorFlow
Designed by Google
10x better perf / watt
latency and efficiency
bit quantization