bda310 an introduction to the ai services at aws
TRANSCRIPT
© 2015, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Keith Steward, Ph.D.
Specialist Solution Architect, AWS
July 26, 2017
An Introduction to the AI Services at AWS
Artificial Intelligence
at Amazon
An Introduction to the AI Services at AWS
Apache
Apache
MXNet
Deep learning framework
An Introduction to the AI Services at AWS
Apache
Amazon
Polly
Text-to-Speech
Apache
MXNet
Deep learning framework
An Introduction to the AI Services at AWS
Apache
Amazon
Polly
Text-to-Speech
Amazon
Rekognition
Computer Vision
Apache
MXNet
Deep learning framework
An Introduction to the AI Services at AWS
Apache
Amazon
Polly
Text-to-Speech
Amazon
RekognitionAmazon
Lex
Computer Vision ASR & NLU
Apache
MXNet
Deep learning framework
An Introduction to the AI Services at AWS
Apache
MXNet
Apache
Deep learning framework
Apache MXNet
Programmable Portable High Performance
Near linear scaling
across hundreds of GPUs
Highly efficient
models for mobile
and IoT
Simple syntax,
multiple languages
Why Apache MXNet?
Most Open Best On AWS
Optimized for
deep learning on AWS
Accepted into the
Apache Incubator
(Integration with AWS)
Apache MXNet is the deep learning framework
of choice for AWS
P2 INSTANCES DL CLOUD FORMATION TEMPLATE
DL AMIS
An Introduction to the AI Services at AWS
Amazon
Polly
Text-to-Speech
Apache
Amazon Polly: Life-like Text-to-Speech Service
Converts text
to life-like speech
47 voices 24 languages Low latency,
real time
Fully managed
Let’s take a listen…
“Today in Seattle, WA, it’s 11°F”
‘"We live for the music" live from the Madison Square Garden.’
1. Automatic, Accurate Text Processing
Amazon Polly: A Focus On Voice Quality & Pronunciation
2. Intelligible and Easy to Understand
1. Automatic, Accurate Text Processing
Amazon Polly: A Focus On Voice Quality & Pronunciation
2. Intelligible and Easy to Understand
3. Add Semantic Meaning to Text
“Richard’s number is 2122341237“
“Richard’s number is 2122341237“
Telephone Number
Amazon Polly: A Focus On Voice Quality & Pronunciation
1. Automatic, Accurate Text Processing
2. Intelligible and Easy to Understand
3. Add Semantic Meaning to Text
4. Customized Pronunciation
“My daughter’s name is Kaja.”
“My daughter’s name is Kaja.”
1. Automatic, Accurate Text Processing
Amazon Polly: A Focus On Voice Quality & Pronunciation
Amazon Polly: Common Use Cases
• Internet of Things (smart home, connected devices)
• Education (language learning, training videos)
• Voiced Media (news, blogs, email)
• Voiced Chat Bots (Amazon Lex, Alexa skills)
• Gaming (avatars, Amazon Lumberyard)
#VoiceFirst Movement
An Introduction to the AI Services at AWS
Amazon
Rekognition
Computer Vision
Apache
Amazon Rekognition: Computer Vision Service
Object and Scene
Detection
Facial
AnalysisFacial
Comparison
Facial
Recognition
Amazon Rekognition: Computer Vision ServiceState-of-the-art face recognition (bounding box and key features).
Face Attribute Extraction (emotion, gender, race, age, etc.)
Emotion: confused: 4%, calm: 73%
Sunglasses: false (value: 0)
Gender: female (value: 0)
Mouth open wide: 0% (value: 0)
Eye closed: open (value: 0)
Glasses: no glass (value: 0)
Mustache: false (value: 0)
Beard: (value: 0)
Amazon Rekognition: Computer Vision Service
demo
Amazon Rekognition: Object & Scene Detection
Amazon Rekognition: Facial Search
Facial
verification
Face
Search
Visual Similarity
Search
(compare two faces) (compare many faces) (find similar faces)
Amazon Rekognition: A few use cases
Best photo: use the attributes smile and eyesOpen to determine the best photos to post
Demographic detection: collect the age and gender of customers in your store
Sentiment capture: detect the emotions of your customers as they try your product
A/B tuning: identify visually similar alternatives to high-scoring images for A/B testing
Smart filtering: identify images with high visual similarity to ensure only one is displayed
Verify face: compare two faces, receive a confidence score that they are the same person
Protected images: identify visually similar images that are protected by trademarks
An Introduction to the AI Services at AWS
Amazon
Lex
ASR & NLU
Apache
The Advent of Conversational Interactions
1st gen: Machine-oriented
interactions
The Advent of Conversational Interactions
1st gen: Machine-oriented
interactions
2nd gen: Control-oriented
& translated
The Advent of Conversational Interactions
1st gen: Machine-oriented
interactions
2nd gen: Control-oriented
& translated
3rd gen:
Intent-oriented
Amazon Lex ... for Conversational Interactions
Powered by the same deep learning technology as Alexa
Enterprise SaaS Connectors
Deployment to chat platforms, like Slack, Facebook
Messenger, Twilio SMS
Build Voice and Text Chatbots
Interactions on mobile, web, and devices
Informational Bot: Example
Amazon Lex Use Cases
Informational BotsChatbots for everyday consumer requests
Application BotsBuild powerful interfaces to mobile applications
• News updates
• Weather information
• Game scores ….
• Book tickets
• Order food
• Manage bank accounts ….
Enterprise Productivity BotsStreamline enterprise work activities and improve efficiencies
• Check sales numbers
• Marketing performance
• Inventory status ….
Internet of Things (IoT) BotsEnable conversational interfaces for device interactions
• Wearables
• Appliances
• Auto ….
AI Solutions for Every Developer
https://aws.amazon.com/amazon-ai/
Amazon AI: Getting Started
Thank you!
aws.amazon.com/amazon-ai
• 10+ year partnership
• Joint development
• Shared customer passion
• High performance + low costs
• World class supply chain
CLOUD &
DATA CENTER
THINGS &
DEVICES
AWS IOT Alexa Voice
Services
Amazon EC2 Amazon S3
Amazon & Intel
Amazon & Intel
40@IntelAI
Hardware for DL Workloads
Up to 2X better peak performance
on compute-intensive analytics
100x improvement in inference
performance on EC2 C5 instance*
NEW C5 more computational
power, lower costs – customers do
more with less
Blazingly Fast Data Access
New microarchitecture, hardware
acceleration, Intel® AVX-512
50% more memory than previous
generation
Novartis conducted 39 years of
computational chemistry in 9 hours*
High Speed Scalability
Up to 1.73x faster completion of
massively parallel research
simulations than the previous
generation
Seamless data transfer via
interconnects
Training AI: Intel® xeon® scalable processorBest-in-Class Deep Learning Training Performance
Accelerator for training compute density in deep learning centric environments
+
41@IntelAI
Inference in the cloud: amazon & Intel®Math Kernel Library for Deep Neural Networks
For developers of deep learning frameworks featuring optimized performance on Intel hardware
6.1 2.4 1.2 0.8
679.4
262.5
79.7 73.9
0
200
400
600
800
AlexNet GoogLeNet v1 ResNet-50 Inception v3
Imag
es/S
ec
c4.8xlarge MXNet Inference
No MKL MKL
Up to 2X better peak performance on compute-intensive analytics
100x improvement in inference performance on EC2 C5 instance*
Intel-optimized Caffe, Intel® MKL for high performance distributed training and inference
CloudFormation template with AWS services and EC2, CfnCluster, DynamoDB, EBS and Spot Instance support
Classify text, train a Convolutional neural network, visualize the training using Tensorboard using BigDL on AWS
Intel Confidential
INTEL® IOT GATEWAY REAL TIME ANALYTICSAWS IOT PLATFORM
Amazon EC2
X1
Inference at the edge: AWS & Intel®
cost savings with scalability
End-to-end interoperability
to scale applications and services
streamlined manageability and
analytics
Seamless data management
and analytics from thing
to network to cloud
multilayered, end-to-end
security
A chain of trust rooted
in the hardware and linked throughout
the software
43@IntelAI
Libraries, frameworks & toolsIntel® Math Kernel
Library
Intel® MLSL
Intel® Data
Analytics
Acceleration
Library
(DAAL)
Intel®
Distributio
n
Open
Source
Frameworks
Intel Deep
Learning SDK
Intel® Computer
Vision SDKIntel® MKL MKL-DNN
High
Level
Overview
Computation
primitives; high
performance math
primitives granting
low level of control
Computation
primitives; free
open source DNN
functions for high-
velocity integration
with deep learning
frameworks
Communication
primitives; building
blocks to scale deep
learning framework
performance over a
cluster
Broad data analytics
acceleration object
oriented library
supporting distributed
ML at the algorithm
level
Most popular and
fastest growing
language for
machine learning
Toolkits driven by
academia and
industry for training
machine learning
algorithms
Accelerate deep
learning model
design, training and
deployment
Toolkit to develop &
deploying vision-
oriented solutions
that harness the full
performance of Intel
CPUs and SOC
accelerators
Primary
Audience
Consumed by
developers of
higher level
libraries and
Applications
Consumed by
developers of the
next generation of
deep learning
frameworks
Deep learning
framework
developers and
optimizers
Wider Data Analytics
and ML audience,
Algorithm level
development for all
stages of data
analytics
Application
Developers and
Data Scientists
Machine Learning
App Developers,
Researchers and
Data Scientists.
Application
Developers and Data
Scientists
Developers who
create vision-oriented
solutions
Example
Usage
Framework
developers call
matrix
multiplication,
convolution
functions
New framework
with functions
developers call for
max CPU
performance
Framework
developer calls
functions to distribute
Caffe training
compute across an
Intel® Xeon Phi™
cluster
Call distributed
alternating least
squares algorithm for
a recommendation
system
Call scikit-learn
k-means function
for credit card
fraud detection
Script and train a
convolution neural
network for image
recognition
Deep Learning
training and model
creation, with
optimization for
deployment on
constrained end
device
Use deep learning to
do pedestrian
detection
…
Find out more at software.intel.com/ai
Q & A
Don’t Forget Your Evaluations!