SlideShare ist ein Scribd-Unternehmen logo
1 von 34
Downloaden Sie, um offline zu lesen
Discovering Your
AI Super Powers
Tips And Tricks To Jumpstart Your AI Project
Wee Hyong Tok, PhD
Principal Data Science Manager
Microsoft
@weehyong
Global Artificial Intelligence Conference 2018, Seattle
How long does it take to train a
deep learning model?
Before 2017
2017
April
ResNet-50
32 CPU
256 Nvidia P100 GPUs
1
hour
ResNet-50
NVIDIA M40 GPU
14
days
1018 single precision
operations
Sept
ResNet-50
1,600 CPUs
31
minutes
Nov
15
minutes
ResNet-50
1,024 P100 GPUs
UC Berkeley, TACC, UC DavisFacebook Preferred Network
ChainerMN
5 Super Powers
Understand the problem!1
Different Types of Deep Learning Problems
Yes
Similar
image
Query
image
Deep Learning Tasks
“I had a wonderful
experience! The rooms were
wonderful and the staff was
helpful.”
Build your AI Toolbox!2
Concepts
Techniques
Infrastructure
+ quality of the models
AI
Common Deep Learning Models
CNN
Convolutional
Neural Network
RNN
Recurrent Neural
Network
Deep Learning Libraries
And more….
AI
Toolbox of a Data Scientist
1313
Deep Learning Virtual Machine (DLVM)
14
• Requirements of agile data science
• Elasticity.
• Efficiency.
• Cost-effectiveness.
• Features of DLVM
• Languages.
• Data platforms.
• ML and AI tools.
• Data Exploration and Visualization.
• Data Ingestion tools.
• Development tools
3 Jumpstart with Transfer Learning
Credits: Olah, et al., "Feature Visualization", Distill, 2017
https://distill.pub/2017/feature-visualization/
Types of Transfer Learning
Type How to Initialize
Featurization
Layers
Output Layer
Initialization
How is Transfer Learning
used?
How to Train?
Standard DNN Random Random None Train featurization and output
jointly
Headless DNN Learn using
another task
Separate ML
algorithm
Use the features learned
on a related task
Use the features to train a
separate classifier
Fine Tune DNN Learn using
another task
Random Use and fine tune
features learned on a
related task
Train featurization and output
jointly with a small learning
rate
Multi-Task DNN Random Random Learned features need to
solve many related tasks
Share a featurization network
across both tasks. Train all
networks jointly with a loss
function (sum of individual task
loss function)
Deep Neural Network for Computer Vision
cat? YES
dog? NO
car? NO
Convolutional Layers
Fully
Connected
Layers
Complex Objects
& Scenes
(people, animals,
cars, beach
scene, etc.)
Image
Low-Level Features
(lines, edges,
color fields, etc.)
High-Level Features
(corners, contours,
simple shapes)
Object Parts
(wheels, faces,
windows, etc.)
11x11 conv, 96, /4, pool/2
5x5 conv, 256, pool/2
3x3 conv, 384
3x3 conv, 384
3x3 conv, 256, pool/2
fc, 4096
fc, 4096
fc, 1000
AlexNet, 8 layers
(ILSVRC 2012)
3x3 conv, 64
3x3 conv, 64, pool/2
3x3 conv, 128
3x3 conv, 128, pool/2
3x3 conv, 256
3x3 conv, 256
3x3 conv, 256
3x3 conv, 256, pool/2
3x3 conv, 512
3x3 conv, 512
3x3 conv, 512
3x3 conv, 512, pool/2
3x3 conv, 512
3x3 conv, 512
3x3 conv, 512
3x3 conv, 512, pool/2
fc, 4096
fc, 4096
fc, 1000
VGG, 19 layers
(ILSVRC 2014)
input
Conv
7x7+ 2(S)
MaxPool
3x3+ 2(S)
LocalRespNorm
Conv
1x1+ 1(V)
Conv
3x3+ 1(S)
LocalRespNorm
MaxPool
3x3+ 2(S)
Conv Conv Conv Conv
1x1+ 1(S) 3x3+ 1(S) 5x5+ 1(S) 1x1+ 1(S)
Conv Conv MaxPool
1x1+ 1(S) 1x1+ 1(S) 3x3+ 1(S)
Dept hConcat
Conv Conv Conv Conv
1x1+ 1(S) 3x3+ 1(S) 5x5+ 1(S) 1x1+ 1(S)
Conv Conv MaxPool
1x1+ 1(S) 1x1+ 1(S) 3x3+ 1(S)
Dept hConcat
MaxPool
3x3+ 2(S)
Conv Conv Conv Conv
1x1+ 1(S) 3x3+ 1(S) 5x5+ 1(S) 1x1+ 1(S)
Conv Conv MaxPool
1x1+ 1(S) 1x1+ 1(S) 3x3+ 1(S)
Dept hConcat
Conv Conv Conv Conv
1x1+ 1(S) 3x3+ 1(S) 5x5+ 1(S) 1x1+ 1(S)
Conv Conv MaxPool
1x1+ 1(S) 1x1+ 1(S) 3x3+ 1(S)
AveragePool
5x5+ 3(V)
Dept hConcat
Conv Conv Conv Conv
1x1+ 1(S) 3x3+ 1(S) 5x5+ 1(S) 1x1+ 1(S)
Conv Conv MaxPool
1x1+ 1(S) 1x1+ 1(S) 3x3+ 1(S)
Dept hConcat
Conv Conv Conv Conv
1x1+ 1(S) 3x3+ 1(S) 5x5+ 1(S) 1x1+ 1(S)
Conv Conv MaxPool
1x1+ 1(S) 1x1+ 1(S) 3x3+ 1(S)
Dept hConcat
Conv Conv Conv Conv
1x1+ 1(S) 3x3+ 1(S) 5x5+ 1(S) 1x1+ 1(S)
Conv Conv MaxPool
1x1+ 1(S) 1x1+ 1(S) 3x3+ 1(S)
AveragePool
5x5+ 3(V)
Dept hConcat
MaxPool
3x3+ 2(S)
Conv Conv Conv Conv
1x1+ 1(S) 3x3+ 1(S) 5x5+ 1(S) 1x1+ 1(S)
Conv Conv MaxPool
1x1+ 1(S) 1x1+ 1(S) 3x3+ 1(S)
Dept hConcat
Conv Conv Conv Conv
1x1+ 1(S) 3x3+ 1(S) 5x5+ 1(S) 1x1+ 1(S)
Conv Conv MaxPool
1x1+ 1(S) 1x1+ 1(S) 3x3+ 1(S)
Dept hConcat
AveragePool
7x7+ 1(V)
FC
Conv
1x1+ 1(S)
FC
FC
Soft maxAct ivat ion
soft max0
Conv
1x1+ 1(S)
FC
FC
Soft maxAct ivat ion
soft max1
Soft maxAct ivat ion
soft max2
GoogleNet, 22 layers
(ILSVRC 2014)
ILSVRC (ImageNet Large Scale Visual Recognition Challenge)
AlexNet, VGG, GoogleNet, ResNet and more
ResNet, 152 layers 1x1 conv, 64
3x3 conv, 64
1x1 conv, 256
1x1 conv, 64
3x3 conv, 64
1x1 conv, 256
1x1 conv, 64
3x3 conv, 64
1x1 conv, 256
1x2 conv, 128, /2
3x3 conv, 128
1x1 conv, 512
1x1 conv, 128
3x3 conv, 128
1x1 conv, 512
1x1 conv, 128
3x3 conv, 128
1x1 conv, 512
1x1 conv, 128
3x3 conv, 128
1x1 conv, 512
1x1 conv, 128
3x3 conv, 128
1x1 conv, 512
1x1 conv, 128
3x3 conv, 128
1x1 conv, 512
7x7 conv, 64, /2, pool/2
ResNet-152
• Research dataset with >10
million images
• Image annotated with labels
from on ontology (>22K
labels)
• Generic images covering an
extremely wide ranges of labels
ImageNet dataset
Pre-Built CNN from General Task on Millions of Images
Output
Layer
Stripped
Classi
fier
e.g.
SVM
dotted?
Complex
Objects &
Scenes
(people, animals,
cars, beach
scene, etc.)
Low-Level Features
(lines, edges,
color fields, etc.)
High-Level Features
(corners, contours,
simple shapes)
Object Parts
(wheels, faces,
windows, etc.)
Outputs of penultimate layer of ImageNet Trained CNN
provide excellent general purpose image features
Pre-Built CNN from General Task on Millions of Images
Output
Layer
Stripped
Using a pre-trained DNN, an accurate
model can be achieved with thousands (or
less) of labeled examples instead of millions
dotted?
Train one or more
layers in new network
Pre-trained Models
http://bit.ly/2jf97NE http://bit.ly/2zNiN8B http://bit.ly/1KlVMf0
“Transferring knowledge” also possible in other domains such as use of word
embeddings for text
Select the Right
Infrastructure for AI4
AI
@ Scale
Read Data
Clean and Pre-process
Train Models
Inferencing @ Scale
Distributed Training Architecture
Data Parallelism Model Parallelism
1. Parallel training on different
machines
2. Update the parameter server
synchronously/asynchronously
3. Refresh the local model with
new parameters, go to 1 and
repeat
1. The global model is partitioned
into K sub-models without
overlap.
2. The sub-models are distributed
over K local workers and serve
as their local models.
3. In each mini-batch, the local
workers compute the gradients
of the local weights by back
propagation.
Credits: Taifeng Wang, DMTK team
Selecting Big Data and AI Infrastructure
Desktop / Laptop Spark
Clusters
CloudKubernetes
Clusters
VM1
k8s-master-27473156-0
VM2
VM3
k8s-agentpool1-27473156-1
k8s-agentpool2-27473156-0
NC6
(GPU Enabled)
DS_v2
(Non-GPU)
Virtual network
K8s-vnet-27473156
Deployment to Azure
Example – AI @ Scale on Kubernetes Clusters
What can we run on the deep
learning infrastructure?
Using Spark for Machine Learning
• User needs to write lots of “glue” code to prepare features for ML
algorithms.
• Coerce types and data layout to that what’s expected by learner
• Use different conventions for different learners
• Lack of domain-specific libraries: computer vision or text
analytics…
• Latest: Image Data Support in Apache Spark 2.3
https://blogs.technet.microsoft.com/machinelearning/2018/03/05/image-
data-support-in-apache-spark/
• Limited capabilities for model evaluation & model management
Microsoft Machine Learning Library
for Apache Spark (MMLSpark)
GitHub Repo: https://github.com/Azure/mmlspark
Get started now using Docker image:
docker run -it -p 8888:8888 -e ACCEPT_EULA=yes microsoft/mmlspark
Navigate to http://localhost:8888 to view example Jupyter notebooks
Believe we can all do AI ☺5
Custom Vision Video
CustomVision.ai
Discovering Your AI Super
Powers - Tips And Tricks
To Jumpstart Your AI
Project
Wee Hyong Tok, PhD
Principal Data Science Manager
Microsoft
@weehyong
Global Artificial Intelligence
Conference 2018, Seattle
Thank You!

Weitere ähnliche Inhalte

Was ist angesagt?

Object Segmentation (D2L7 Insight@DCU Machine Learning Workshop 2017)
Object Segmentation (D2L7 Insight@DCU Machine Learning Workshop 2017)Object Segmentation (D2L7 Insight@DCU Machine Learning Workshop 2017)
Object Segmentation (D2L7 Insight@DCU Machine Learning Workshop 2017)Universitat Politècnica de Catalunya
 
Sergei Vassilvitskii, Research Scientist, Google at MLconf NYC - 4/15/16
Sergei Vassilvitskii, Research Scientist, Google at MLconf NYC - 4/15/16Sergei Vassilvitskii, Research Scientist, Google at MLconf NYC - 4/15/16
Sergei Vassilvitskii, Research Scientist, Google at MLconf NYC - 4/15/16MLconf
 
Alex Smola, Professor in the Machine Learning Department, Carnegie Mellon Uni...
Alex Smola, Professor in the Machine Learning Department, Carnegie Mellon Uni...Alex Smola, Professor in the Machine Learning Department, Carnegie Mellon Uni...
Alex Smola, Professor in the Machine Learning Department, Carnegie Mellon Uni...MLconf
 
Realtime Per Face Texture Mapping (PTEX)
Realtime Per Face Texture Mapping (PTEX)Realtime Per Face Texture Mapping (PTEX)
Realtime Per Face Texture Mapping (PTEX)basisspace
 
NVIDIA 深度學習教育機構 (DLI): Medical image segmentation using digits
NVIDIA 深度學習教育機構 (DLI): Medical image segmentation using digitsNVIDIA 深度學習教育機構 (DLI): Medical image segmentation using digits
NVIDIA 深度學習教育機構 (DLI): Medical image segmentation using digitsNVIDIA Taiwan
 
Massively Parallel K-Nearest Neighbor Computation on Distributed Architectures
Massively Parallel K-Nearest Neighbor Computation on Distributed Architectures Massively Parallel K-Nearest Neighbor Computation on Distributed Architectures
Massively Parallel K-Nearest Neighbor Computation on Distributed Architectures Intel® Software
 
Bootstrap Custom Image Classification using Transfer Learning by Danielle Dea...
Bootstrap Custom Image Classification using Transfer Learning by Danielle Dea...Bootstrap Custom Image Classification using Transfer Learning by Danielle Dea...
Bootstrap Custom Image Classification using Transfer Learning by Danielle Dea...Wee Hyong Tok
 
Deep Learning for Computer Vision: Transfer Learning and Domain Adaptation (U...
Deep Learning for Computer Vision: Transfer Learning and Domain Adaptation (U...Deep Learning for Computer Vision: Transfer Learning and Domain Adaptation (U...
Deep Learning for Computer Vision: Transfer Learning and Domain Adaptation (U...Universitat Politècnica de Catalunya
 
Pixel RNN to Pixel CNN++
Pixel RNN to Pixel CNN++Pixel RNN to Pixel CNN++
Pixel RNN to Pixel CNN++Dongheon Lee
 
Scalable Deep Learning Using Apache MXNet
Scalable Deep Learning Using Apache MXNetScalable Deep Learning Using Apache MXNet
Scalable Deep Learning Using Apache MXNetAmazon Web Services
 
Deep Learning behind Prisma
Deep Learning behind PrismaDeep Learning behind Prisma
Deep Learning behind Prismalostleaves
 
[SNU Computer Vision Course Project] Image Style Recognition
[SNU Computer Vision Course Project] Image Style Recognition[SNU Computer Vision Course Project] Image Style Recognition
[SNU Computer Vision Course Project] Image Style RecognitionHunjae Jung
 
Anima Anadkumar, Principal Scientist, Amazon Web Services, Endowed Professor,...
Anima Anadkumar, Principal Scientist, Amazon Web Services, Endowed Professor,...Anima Anadkumar, Principal Scientist, Amazon Web Services, Endowed Professor,...
Anima Anadkumar, Principal Scientist, Amazon Web Services, Endowed Professor,...MLconf
 
PixelCNN, Wavenet, Normalizing Flows - Santiago Pascual - UPC Barcelona 2018
PixelCNN, Wavenet, Normalizing Flows - Santiago Pascual - UPC Barcelona 2018PixelCNN, Wavenet, Normalizing Flows - Santiago Pascual - UPC Barcelona 2018
PixelCNN, Wavenet, Normalizing Flows - Santiago Pascual - UPC Barcelona 2018Universitat Politècnica de Catalunya
 
"Energy-efficient Hardware for Embedded Vision and Deep Convolutional Neural ...
"Energy-efficient Hardware for Embedded Vision and Deep Convolutional Neural ..."Energy-efficient Hardware for Embedded Vision and Deep Convolutional Neural ...
"Energy-efficient Hardware for Embedded Vision and Deep Convolutional Neural ...Edge AI and Vision Alliance
 
Large scale logistic regression and linear support vector machines using spark
Large scale logistic regression and linear support vector machines using sparkLarge scale logistic regression and linear support vector machines using spark
Large scale logistic regression and linear support vector machines using sparkMila, Université de Montréal
 

Was ist angesagt? (20)

Object Segmentation (D2L7 Insight@DCU Machine Learning Workshop 2017)
Object Segmentation (D2L7 Insight@DCU Machine Learning Workshop 2017)Object Segmentation (D2L7 Insight@DCU Machine Learning Workshop 2017)
Object Segmentation (D2L7 Insight@DCU Machine Learning Workshop 2017)
 
Sergei Vassilvitskii, Research Scientist, Google at MLconf NYC - 4/15/16
Sergei Vassilvitskii, Research Scientist, Google at MLconf NYC - 4/15/16Sergei Vassilvitskii, Research Scientist, Google at MLconf NYC - 4/15/16
Sergei Vassilvitskii, Research Scientist, Google at MLconf NYC - 4/15/16
 
Alex Smola, Professor in the Machine Learning Department, Carnegie Mellon Uni...
Alex Smola, Professor in the Machine Learning Department, Carnegie Mellon Uni...Alex Smola, Professor in the Machine Learning Department, Carnegie Mellon Uni...
Alex Smola, Professor in the Machine Learning Department, Carnegie Mellon Uni...
 
Recurrent Instance Segmentation (UPC Reading Group)
Recurrent Instance Segmentation (UPC Reading Group)Recurrent Instance Segmentation (UPC Reading Group)
Recurrent Instance Segmentation (UPC Reading Group)
 
Realtime Per Face Texture Mapping (PTEX)
Realtime Per Face Texture Mapping (PTEX)Realtime Per Face Texture Mapping (PTEX)
Realtime Per Face Texture Mapping (PTEX)
 
NVIDIA 深度學習教育機構 (DLI): Medical image segmentation using digits
NVIDIA 深度學習教育機構 (DLI): Medical image segmentation using digitsNVIDIA 深度學習教育機構 (DLI): Medical image segmentation using digits
NVIDIA 深度學習教育機構 (DLI): Medical image segmentation using digits
 
Massively Parallel K-Nearest Neighbor Computation on Distributed Architectures
Massively Parallel K-Nearest Neighbor Computation on Distributed Architectures Massively Parallel K-Nearest Neighbor Computation on Distributed Architectures
Massively Parallel K-Nearest Neighbor Computation on Distributed Architectures
 
Deep Learning for Computer Vision: Backward Propagation (UPC 2016)
Deep Learning for Computer Vision: Backward Propagation (UPC 2016)Deep Learning for Computer Vision: Backward Propagation (UPC 2016)
Deep Learning for Computer Vision: Backward Propagation (UPC 2016)
 
Bootstrap Custom Image Classification using Transfer Learning by Danielle Dea...
Bootstrap Custom Image Classification using Transfer Learning by Danielle Dea...Bootstrap Custom Image Classification using Transfer Learning by Danielle Dea...
Bootstrap Custom Image Classification using Transfer Learning by Danielle Dea...
 
Deep Learning for Computer Vision: Transfer Learning and Domain Adaptation (U...
Deep Learning for Computer Vision: Transfer Learning and Domain Adaptation (U...Deep Learning for Computer Vision: Transfer Learning and Domain Adaptation (U...
Deep Learning for Computer Vision: Transfer Learning and Domain Adaptation (U...
 
Pixel RNN to Pixel CNN++
Pixel RNN to Pixel CNN++Pixel RNN to Pixel CNN++
Pixel RNN to Pixel CNN++
 
Scalable Deep Learning Using Apache MXNet
Scalable Deep Learning Using Apache MXNetScalable Deep Learning Using Apache MXNet
Scalable Deep Learning Using Apache MXNet
 
Deep Learning behind Prisma
Deep Learning behind PrismaDeep Learning behind Prisma
Deep Learning behind Prisma
 
[SNU Computer Vision Course Project] Image Style Recognition
[SNU Computer Vision Course Project] Image Style Recognition[SNU Computer Vision Course Project] Image Style Recognition
[SNU Computer Vision Course Project] Image Style Recognition
 
Anima Anadkumar, Principal Scientist, Amazon Web Services, Endowed Professor,...
Anima Anadkumar, Principal Scientist, Amazon Web Services, Endowed Professor,...Anima Anadkumar, Principal Scientist, Amazon Web Services, Endowed Professor,...
Anima Anadkumar, Principal Scientist, Amazon Web Services, Endowed Professor,...
 
Deep Learning for Computer Vision: Data Augmentation (UPC 2016)
Deep Learning for Computer Vision: Data Augmentation (UPC 2016)Deep Learning for Computer Vision: Data Augmentation (UPC 2016)
Deep Learning for Computer Vision: Data Augmentation (UPC 2016)
 
PixelCNN, Wavenet, Normalizing Flows - Santiago Pascual - UPC Barcelona 2018
PixelCNN, Wavenet, Normalizing Flows - Santiago Pascual - UPC Barcelona 2018PixelCNN, Wavenet, Normalizing Flows - Santiago Pascual - UPC Barcelona 2018
PixelCNN, Wavenet, Normalizing Flows - Santiago Pascual - UPC Barcelona 2018
 
"Energy-efficient Hardware for Embedded Vision and Deep Convolutional Neural ...
"Energy-efficient Hardware for Embedded Vision and Deep Convolutional Neural ..."Energy-efficient Hardware for Embedded Vision and Deep Convolutional Neural ...
"Energy-efficient Hardware for Embedded Vision and Deep Convolutional Neural ...
 
Large scale logistic regression and linear support vector machines using spark
Large scale logistic regression and linear support vector machines using sparkLarge scale logistic regression and linear support vector machines using spark
Large scale logistic regression and linear support vector machines using spark
 
Deep Learning for Computer Vision: Visualization (UPC 2016)
Deep Learning for Computer Vision: Visualization (UPC 2016)Deep Learning for Computer Vision: Visualization (UPC 2016)
Deep Learning for Computer Vision: Visualization (UPC 2016)
 

Ähnlich wie Discovering Your AI Super Powers - Tips and Tricks to Jumpstart your AI Projects

[第34回 WBA若手の会勉強会] Microsoft AI platform
[第34回 WBA若手の会勉強会] Microsoft AI platform[第34回 WBA若手の会勉強会] Microsoft AI platform
[第34回 WBA若手の会勉強会] Microsoft AI platformNaoki (Neo) SATO
 
Deep Learning for New User Interactions (Gestures, Speech and Emotions)
Deep Learning for New User Interactions (Gestures, Speech and Emotions)Deep Learning for New User Interactions (Gestures, Speech and Emotions)
Deep Learning for New User Interactions (Gestures, Speech and Emotions)Olivia Klose
 
Deep Dive on Deep Learning (June 2018)
Deep Dive on Deep Learning (June 2018)Deep Dive on Deep Learning (June 2018)
Deep Dive on Deep Learning (June 2018)Julien SIMON
 
CIFAR-10 for DAWNBench: Wide ResNets, Mixup Augmentation and "Super Convergen...
CIFAR-10 for DAWNBench: Wide ResNets, Mixup Augmentation and "Super Convergen...CIFAR-10 for DAWNBench: Wide ResNets, Mixup Augmentation and "Super Convergen...
CIFAR-10 for DAWNBench: Wide ResNets, Mixup Augmentation and "Super Convergen...Thom Lane
 
SDVIs and In-Situ Visualization on TACC's Stampede
SDVIs and In-Situ Visualization on TACC's StampedeSDVIs and In-Situ Visualization on TACC's Stampede
SDVIs and In-Situ Visualization on TACC's StampedeIntel® Software
 
Natural Language Processing with CNTK and Apache Spark with Ali Zaidi
Natural Language Processing with CNTK and Apache Spark with Ali ZaidiNatural Language Processing with CNTK and Apache Spark with Ali Zaidi
Natural Language Processing with CNTK and Apache Spark with Ali ZaidiDatabricks
 
深度學習在AOI的應用
深度學習在AOI的應用深度學習在AOI的應用
深度學習在AOI的應用CHENHuiMei
 
Developing and Deploying Deep Learning Based Computer Vision Systems - Alka N...
Developing and Deploying Deep Learning Based Computer Vision Systems - Alka N...Developing and Deploying Deep Learning Based Computer Vision Systems - Alka N...
Developing and Deploying Deep Learning Based Computer Vision Systems - Alka N...CodeOps Technologies LLP
 
AWS re:Invent 2016: Deep Learning at Cloud Scale: Improving Video Discoverabi...
AWS re:Invent 2016: Deep Learning at Cloud Scale: Improving Video Discoverabi...AWS re:Invent 2016: Deep Learning at Cloud Scale: Improving Video Discoverabi...
AWS re:Invent 2016: Deep Learning at Cloud Scale: Improving Video Discoverabi...Amazon Web Services
 
What’s New in ScyllaDB Open Source 5.0
What’s New in ScyllaDB Open Source 5.0What’s New in ScyllaDB Open Source 5.0
What’s New in ScyllaDB Open Source 5.0ScyllaDB
 
alphablues - ML applied to text and image in chat bots
alphablues - ML applied to text and image in chat botsalphablues - ML applied to text and image in chat bots
alphablues - ML applied to text and image in chat botsAndré Karpištšenko
 
On-the-fly Visual Category Search in Web-scale Image Collections
On-the-fly Visual Category Search in Web-scale Image CollectionsOn-the-fly Visual Category Search in Web-scale Image Collections
On-the-fly Visual Category Search in Web-scale Image CollectionsKen Chatfield
 
ScyllaDB V Developer Deep Dive Series: Resiliency and Strong Consistency via ...
ScyllaDB V Developer Deep Dive Series: Resiliency and Strong Consistency via ...ScyllaDB V Developer Deep Dive Series: Resiliency and Strong Consistency via ...
ScyllaDB V Developer Deep Dive Series: Resiliency and Strong Consistency via ...ScyllaDB
 
Renegotiating the boundary between database latency and consistency
Renegotiating the boundary between database latency  and consistencyRenegotiating the boundary between database latency  and consistency
Renegotiating the boundary between database latency and consistencyScyllaDB
 
High-Performance Graph Analysis and Modeling
High-Performance Graph Analysis and ModelingHigh-Performance Graph Analysis and Modeling
High-Performance Graph Analysis and ModelingNesreen K. Ahmed
 
[html5jロボット部 第7回勉強会] Microsoft Cognitive Toolkit (CNTK) Overview
[html5jロボット部 第7回勉強会] Microsoft Cognitive Toolkit (CNTK) Overview[html5jロボット部 第7回勉強会] Microsoft Cognitive Toolkit (CNTK) Overview
[html5jロボット部 第7回勉強会] Microsoft Cognitive Toolkit (CNTK) OverviewNaoki (Neo) SATO
 
Anomaly Detection with Azure and .net
Anomaly Detection with Azure and .netAnomaly Detection with Azure and .net
Anomaly Detection with Azure and .netMarco Parenzan
 
VoxxedDays Luxembourg 2019
VoxxedDays Luxembourg 2019VoxxedDays Luxembourg 2019
VoxxedDays Luxembourg 2019Cédrick Lunven
 

Ähnlich wie Discovering Your AI Super Powers - Tips and Tricks to Jumpstart your AI Projects (20)

[第34回 WBA若手の会勉強会] Microsoft AI platform
[第34回 WBA若手の会勉強会] Microsoft AI platform[第34回 WBA若手の会勉強会] Microsoft AI platform
[第34回 WBA若手の会勉強会] Microsoft AI platform
 
Deep Learning for New User Interactions (Gestures, Speech and Emotions)
Deep Learning for New User Interactions (Gestures, Speech and Emotions)Deep Learning for New User Interactions (Gestures, Speech and Emotions)
Deep Learning for New User Interactions (Gestures, Speech and Emotions)
 
Deep Dive on Deep Learning (June 2018)
Deep Dive on Deep Learning (June 2018)Deep Dive on Deep Learning (June 2018)
Deep Dive on Deep Learning (June 2018)
 
CIFAR-10 for DAWNBench: Wide ResNets, Mixup Augmentation and "Super Convergen...
CIFAR-10 for DAWNBench: Wide ResNets, Mixup Augmentation and "Super Convergen...CIFAR-10 for DAWNBench: Wide ResNets, Mixup Augmentation and "Super Convergen...
CIFAR-10 for DAWNBench: Wide ResNets, Mixup Augmentation and "Super Convergen...
 
SDVIs and In-Situ Visualization on TACC's Stampede
SDVIs and In-Situ Visualization on TACC's StampedeSDVIs and In-Situ Visualization on TACC's Stampede
SDVIs and In-Situ Visualization on TACC's Stampede
 
Novi sad ai event 3-2018
Novi sad ai event 3-2018Novi sad ai event 3-2018
Novi sad ai event 3-2018
 
Natural Language Processing with CNTK and Apache Spark with Ali Zaidi
Natural Language Processing with CNTK and Apache Spark with Ali ZaidiNatural Language Processing with CNTK and Apache Spark with Ali Zaidi
Natural Language Processing with CNTK and Apache Spark with Ali Zaidi
 
深度學習在AOI的應用
深度學習在AOI的應用深度學習在AOI的應用
深度學習在AOI的應用
 
Developing and Deploying Deep Learning Based Computer Vision Systems - Alka N...
Developing and Deploying Deep Learning Based Computer Vision Systems - Alka N...Developing and Deploying Deep Learning Based Computer Vision Systems - Alka N...
Developing and Deploying Deep Learning Based Computer Vision Systems - Alka N...
 
AWS re:Invent 2016: Deep Learning at Cloud Scale: Improving Video Discoverabi...
AWS re:Invent 2016: Deep Learning at Cloud Scale: Improving Video Discoverabi...AWS re:Invent 2016: Deep Learning at Cloud Scale: Improving Video Discoverabi...
AWS re:Invent 2016: Deep Learning at Cloud Scale: Improving Video Discoverabi...
 
What’s New in ScyllaDB Open Source 5.0
What’s New in ScyllaDB Open Source 5.0What’s New in ScyllaDB Open Source 5.0
What’s New in ScyllaDB Open Source 5.0
 
alphablues - ML applied to text and image in chat bots
alphablues - ML applied to text and image in chat botsalphablues - ML applied to text and image in chat bots
alphablues - ML applied to text and image in chat bots
 
On-the-fly Visual Category Search in Web-scale Image Collections
On-the-fly Visual Category Search in Web-scale Image CollectionsOn-the-fly Visual Category Search in Web-scale Image Collections
On-the-fly Visual Category Search in Web-scale Image Collections
 
ScyllaDB V Developer Deep Dive Series: Resiliency and Strong Consistency via ...
ScyllaDB V Developer Deep Dive Series: Resiliency and Strong Consistency via ...ScyllaDB V Developer Deep Dive Series: Resiliency and Strong Consistency via ...
ScyllaDB V Developer Deep Dive Series: Resiliency and Strong Consistency via ...
 
Renegotiating the boundary between database latency and consistency
Renegotiating the boundary between database latency  and consistencyRenegotiating the boundary between database latency  and consistency
Renegotiating the boundary between database latency and consistency
 
High-Performance Graph Analysis and Modeling
High-Performance Graph Analysis and ModelingHigh-Performance Graph Analysis and Modeling
High-Performance Graph Analysis and Modeling
 
MXNet Workshop
MXNet WorkshopMXNet Workshop
MXNet Workshop
 
[html5jロボット部 第7回勉強会] Microsoft Cognitive Toolkit (CNTK) Overview
[html5jロボット部 第7回勉強会] Microsoft Cognitive Toolkit (CNTK) Overview[html5jロボット部 第7回勉強会] Microsoft Cognitive Toolkit (CNTK) Overview
[html5jロボット部 第7回勉強会] Microsoft Cognitive Toolkit (CNTK) Overview
 
Anomaly Detection with Azure and .net
Anomaly Detection with Azure and .netAnomaly Detection with Azure and .net
Anomaly Detection with Azure and .net
 
VoxxedDays Luxembourg 2019
VoxxedDays Luxembourg 2019VoxxedDays Luxembourg 2019
VoxxedDays Luxembourg 2019
 

Kürzlich hochgeladen

VIP Model Call Girls Hinjewadi ( Pune ) Call ON 8005736733 Starting From 5K t...
VIP Model Call Girls Hinjewadi ( Pune ) Call ON 8005736733 Starting From 5K t...VIP Model Call Girls Hinjewadi ( Pune ) Call ON 8005736733 Starting From 5K t...
VIP Model Call Girls Hinjewadi ( Pune ) Call ON 8005736733 Starting From 5K t...SUHANI PANDEY
 
Invezz.com - Grow your wealth with trading signals
Invezz.com - Grow your wealth with trading signalsInvezz.com - Grow your wealth with trading signals
Invezz.com - Grow your wealth with trading signalsInvezz1
 
Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...
Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...
Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...amitlee9823
 
Delhi Call Girls Punjabi Bagh 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Call
Delhi Call Girls Punjabi Bagh 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip CallDelhi Call Girls Punjabi Bagh 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Call
Delhi Call Girls Punjabi Bagh 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Callshivangimorya083
 
Digital Advertising Lecture for Advanced Digital & Social Media Strategy at U...
Digital Advertising Lecture for Advanced Digital & Social Media Strategy at U...Digital Advertising Lecture for Advanced Digital & Social Media Strategy at U...
Digital Advertising Lecture for Advanced Digital & Social Media Strategy at U...Valters Lauzums
 
Smarteg dropshipping via API with DroFx.pptx
Smarteg dropshipping via API with DroFx.pptxSmarteg dropshipping via API with DroFx.pptx
Smarteg dropshipping via API with DroFx.pptxolyaivanovalion
 
Call Girls in Sarai Kale Khan Delhi 💯 Call Us 🔝9205541914 🔝( Delhi) Escorts S...
Call Girls in Sarai Kale Khan Delhi 💯 Call Us 🔝9205541914 🔝( Delhi) Escorts S...Call Girls in Sarai Kale Khan Delhi 💯 Call Us 🔝9205541914 🔝( Delhi) Escorts S...
Call Girls in Sarai Kale Khan Delhi 💯 Call Us 🔝9205541914 🔝( Delhi) Escorts S...Delhi Call girls
 
BPAC WITH UFSBI GENERAL PRESENTATION 18_05_2017-1.pptx
BPAC WITH UFSBI GENERAL PRESENTATION 18_05_2017-1.pptxBPAC WITH UFSBI GENERAL PRESENTATION 18_05_2017-1.pptx
BPAC WITH UFSBI GENERAL PRESENTATION 18_05_2017-1.pptxMohammedJunaid861692
 
Log Analysis using OSSEC sasoasasasas.pptx
Log Analysis using OSSEC sasoasasasas.pptxLog Analysis using OSSEC sasoasasasas.pptx
Log Analysis using OSSEC sasoasasasas.pptxJohnnyPlasten
 
Discover Why Less is More in B2B Research
Discover Why Less is More in B2B ResearchDiscover Why Less is More in B2B Research
Discover Why Less is More in B2B Researchmichael115558
 
Call Girls Indiranagar Just Call 👗 7737669865 👗 Top Class Call Girl Service B...
Call Girls Indiranagar Just Call 👗 7737669865 👗 Top Class Call Girl Service B...Call Girls Indiranagar Just Call 👗 7737669865 👗 Top Class Call Girl Service B...
Call Girls Indiranagar Just Call 👗 7737669865 👗 Top Class Call Girl Service B...amitlee9823
 
Best VIP Call Girls Noida Sector 22 Call Me: 8448380779
Best VIP Call Girls Noida Sector 22 Call Me: 8448380779Best VIP Call Girls Noida Sector 22 Call Me: 8448380779
Best VIP Call Girls Noida Sector 22 Call Me: 8448380779Delhi Call girls
 
Best VIP Call Girls Noida Sector 39 Call Me: 8448380779
Best VIP Call Girls Noida Sector 39 Call Me: 8448380779Best VIP Call Girls Noida Sector 39 Call Me: 8448380779
Best VIP Call Girls Noida Sector 39 Call Me: 8448380779Delhi Call girls
 
FESE Capital Markets Fact Sheet 2024 Q1.pdf
FESE Capital Markets Fact Sheet 2024 Q1.pdfFESE Capital Markets Fact Sheet 2024 Q1.pdf
FESE Capital Markets Fact Sheet 2024 Q1.pdfMarinCaroMartnezBerg
 
Market Analysis in the 5 Largest Economic Countries in Southeast Asia.pdf
Market Analysis in the 5 Largest Economic Countries in Southeast Asia.pdfMarket Analysis in the 5 Largest Economic Countries in Southeast Asia.pdf
Market Analysis in the 5 Largest Economic Countries in Southeast Asia.pdfRachmat Ramadhan H
 
Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...
Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...
Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...amitlee9823
 
Introduction-to-Machine-Learning (1).pptx
Introduction-to-Machine-Learning (1).pptxIntroduction-to-Machine-Learning (1).pptx
Introduction-to-Machine-Learning (1).pptxfirstjob4
 

Kürzlich hochgeladen (20)

VIP Model Call Girls Hinjewadi ( Pune ) Call ON 8005736733 Starting From 5K t...
VIP Model Call Girls Hinjewadi ( Pune ) Call ON 8005736733 Starting From 5K t...VIP Model Call Girls Hinjewadi ( Pune ) Call ON 8005736733 Starting From 5K t...
VIP Model Call Girls Hinjewadi ( Pune ) Call ON 8005736733 Starting From 5K t...
 
Sampling (random) method and Non random.ppt
Sampling (random) method and Non random.pptSampling (random) method and Non random.ppt
Sampling (random) method and Non random.ppt
 
Invezz.com - Grow your wealth with trading signals
Invezz.com - Grow your wealth with trading signalsInvezz.com - Grow your wealth with trading signals
Invezz.com - Grow your wealth with trading signals
 
Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...
Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...
Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...
 
Delhi Call Girls Punjabi Bagh 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Call
Delhi Call Girls Punjabi Bagh 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip CallDelhi Call Girls Punjabi Bagh 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Call
Delhi Call Girls Punjabi Bagh 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Call
 
Digital Advertising Lecture for Advanced Digital & Social Media Strategy at U...
Digital Advertising Lecture for Advanced Digital & Social Media Strategy at U...Digital Advertising Lecture for Advanced Digital & Social Media Strategy at U...
Digital Advertising Lecture for Advanced Digital & Social Media Strategy at U...
 
Smarteg dropshipping via API with DroFx.pptx
Smarteg dropshipping via API with DroFx.pptxSmarteg dropshipping via API with DroFx.pptx
Smarteg dropshipping via API with DroFx.pptx
 
Call Girls in Sarai Kale Khan Delhi 💯 Call Us 🔝9205541914 🔝( Delhi) Escorts S...
Call Girls in Sarai Kale Khan Delhi 💯 Call Us 🔝9205541914 🔝( Delhi) Escorts S...Call Girls in Sarai Kale Khan Delhi 💯 Call Us 🔝9205541914 🔝( Delhi) Escorts S...
Call Girls in Sarai Kale Khan Delhi 💯 Call Us 🔝9205541914 🔝( Delhi) Escorts S...
 
BPAC WITH UFSBI GENERAL PRESENTATION 18_05_2017-1.pptx
BPAC WITH UFSBI GENERAL PRESENTATION 18_05_2017-1.pptxBPAC WITH UFSBI GENERAL PRESENTATION 18_05_2017-1.pptx
BPAC WITH UFSBI GENERAL PRESENTATION 18_05_2017-1.pptx
 
Log Analysis using OSSEC sasoasasasas.pptx
Log Analysis using OSSEC sasoasasasas.pptxLog Analysis using OSSEC sasoasasasas.pptx
Log Analysis using OSSEC sasoasasasas.pptx
 
Discover Why Less is More in B2B Research
Discover Why Less is More in B2B ResearchDiscover Why Less is More in B2B Research
Discover Why Less is More in B2B Research
 
Call Girls In Shalimar Bagh ( Delhi) 9953330565 Escorts Service
Call Girls In Shalimar Bagh ( Delhi) 9953330565 Escorts ServiceCall Girls In Shalimar Bagh ( Delhi) 9953330565 Escorts Service
Call Girls In Shalimar Bagh ( Delhi) 9953330565 Escorts Service
 
Call Girls Indiranagar Just Call 👗 7737669865 👗 Top Class Call Girl Service B...
Call Girls Indiranagar Just Call 👗 7737669865 👗 Top Class Call Girl Service B...Call Girls Indiranagar Just Call 👗 7737669865 👗 Top Class Call Girl Service B...
Call Girls Indiranagar Just Call 👗 7737669865 👗 Top Class Call Girl Service B...
 
Best VIP Call Girls Noida Sector 22 Call Me: 8448380779
Best VIP Call Girls Noida Sector 22 Call Me: 8448380779Best VIP Call Girls Noida Sector 22 Call Me: 8448380779
Best VIP Call Girls Noida Sector 22 Call Me: 8448380779
 
Delhi 99530 vip 56974 Genuine Escort Service Call Girls in Kishangarh
Delhi 99530 vip 56974 Genuine Escort Service Call Girls in  KishangarhDelhi 99530 vip 56974 Genuine Escort Service Call Girls in  Kishangarh
Delhi 99530 vip 56974 Genuine Escort Service Call Girls in Kishangarh
 
Best VIP Call Girls Noida Sector 39 Call Me: 8448380779
Best VIP Call Girls Noida Sector 39 Call Me: 8448380779Best VIP Call Girls Noida Sector 39 Call Me: 8448380779
Best VIP Call Girls Noida Sector 39 Call Me: 8448380779
 
FESE Capital Markets Fact Sheet 2024 Q1.pdf
FESE Capital Markets Fact Sheet 2024 Q1.pdfFESE Capital Markets Fact Sheet 2024 Q1.pdf
FESE Capital Markets Fact Sheet 2024 Q1.pdf
 
Market Analysis in the 5 Largest Economic Countries in Southeast Asia.pdf
Market Analysis in the 5 Largest Economic Countries in Southeast Asia.pdfMarket Analysis in the 5 Largest Economic Countries in Southeast Asia.pdf
Market Analysis in the 5 Largest Economic Countries in Southeast Asia.pdf
 
Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...
Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...
Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...
 
Introduction-to-Machine-Learning (1).pptx
Introduction-to-Machine-Learning (1).pptxIntroduction-to-Machine-Learning (1).pptx
Introduction-to-Machine-Learning (1).pptx
 

Discovering Your AI Super Powers - Tips and Tricks to Jumpstart your AI Projects

  • 1. Discovering Your AI Super Powers Tips And Tricks To Jumpstart Your AI Project Wee Hyong Tok, PhD Principal Data Science Manager Microsoft @weehyong Global Artificial Intelligence Conference 2018, Seattle
  • 2.
  • 3. How long does it take to train a deep learning model?
  • 4. Before 2017 2017 April ResNet-50 32 CPU 256 Nvidia P100 GPUs 1 hour ResNet-50 NVIDIA M40 GPU 14 days 1018 single precision operations Sept ResNet-50 1,600 CPUs 31 minutes Nov 15 minutes ResNet-50 1,024 P100 GPUs UC Berkeley, TACC, UC DavisFacebook Preferred Network ChainerMN
  • 7. Different Types of Deep Learning Problems Yes Similar image Query image
  • 8. Deep Learning Tasks “I had a wonderful experience! The rooms were wonderful and the staff was helpful.”
  • 9. Build your AI Toolbox!2
  • 11. AI Common Deep Learning Models CNN Convolutional Neural Network RNN Recurrent Neural Network
  • 13. Toolbox of a Data Scientist 1313
  • 14. Deep Learning Virtual Machine (DLVM) 14 • Requirements of agile data science • Elasticity. • Efficiency. • Cost-effectiveness. • Features of DLVM • Languages. • Data platforms. • ML and AI tools. • Data Exploration and Visualization. • Data Ingestion tools. • Development tools
  • 15. 3 Jumpstart with Transfer Learning Credits: Olah, et al., "Feature Visualization", Distill, 2017 https://distill.pub/2017/feature-visualization/
  • 16. Types of Transfer Learning Type How to Initialize Featurization Layers Output Layer Initialization How is Transfer Learning used? How to Train? Standard DNN Random Random None Train featurization and output jointly Headless DNN Learn using another task Separate ML algorithm Use the features learned on a related task Use the features to train a separate classifier Fine Tune DNN Learn using another task Random Use and fine tune features learned on a related task Train featurization and output jointly with a small learning rate Multi-Task DNN Random Random Learned features need to solve many related tasks Share a featurization network across both tasks. Train all networks jointly with a loss function (sum of individual task loss function)
  • 17. Deep Neural Network for Computer Vision cat? YES dog? NO car? NO Convolutional Layers Fully Connected Layers Complex Objects & Scenes (people, animals, cars, beach scene, etc.) Image Low-Level Features (lines, edges, color fields, etc.) High-Level Features (corners, contours, simple shapes) Object Parts (wheels, faces, windows, etc.)
  • 18. 11x11 conv, 96, /4, pool/2 5x5 conv, 256, pool/2 3x3 conv, 384 3x3 conv, 384 3x3 conv, 256, pool/2 fc, 4096 fc, 4096 fc, 1000 AlexNet, 8 layers (ILSVRC 2012) 3x3 conv, 64 3x3 conv, 64, pool/2 3x3 conv, 128 3x3 conv, 128, pool/2 3x3 conv, 256 3x3 conv, 256 3x3 conv, 256 3x3 conv, 256, pool/2 3x3 conv, 512 3x3 conv, 512 3x3 conv, 512 3x3 conv, 512, pool/2 3x3 conv, 512 3x3 conv, 512 3x3 conv, 512 3x3 conv, 512, pool/2 fc, 4096 fc, 4096 fc, 1000 VGG, 19 layers (ILSVRC 2014) input Conv 7x7+ 2(S) MaxPool 3x3+ 2(S) LocalRespNorm Conv 1x1+ 1(V) Conv 3x3+ 1(S) LocalRespNorm MaxPool 3x3+ 2(S) Conv Conv Conv Conv 1x1+ 1(S) 3x3+ 1(S) 5x5+ 1(S) 1x1+ 1(S) Conv Conv MaxPool 1x1+ 1(S) 1x1+ 1(S) 3x3+ 1(S) Dept hConcat Conv Conv Conv Conv 1x1+ 1(S) 3x3+ 1(S) 5x5+ 1(S) 1x1+ 1(S) Conv Conv MaxPool 1x1+ 1(S) 1x1+ 1(S) 3x3+ 1(S) Dept hConcat MaxPool 3x3+ 2(S) Conv Conv Conv Conv 1x1+ 1(S) 3x3+ 1(S) 5x5+ 1(S) 1x1+ 1(S) Conv Conv MaxPool 1x1+ 1(S) 1x1+ 1(S) 3x3+ 1(S) Dept hConcat Conv Conv Conv Conv 1x1+ 1(S) 3x3+ 1(S) 5x5+ 1(S) 1x1+ 1(S) Conv Conv MaxPool 1x1+ 1(S) 1x1+ 1(S) 3x3+ 1(S) AveragePool 5x5+ 3(V) Dept hConcat Conv Conv Conv Conv 1x1+ 1(S) 3x3+ 1(S) 5x5+ 1(S) 1x1+ 1(S) Conv Conv MaxPool 1x1+ 1(S) 1x1+ 1(S) 3x3+ 1(S) Dept hConcat Conv Conv Conv Conv 1x1+ 1(S) 3x3+ 1(S) 5x5+ 1(S) 1x1+ 1(S) Conv Conv MaxPool 1x1+ 1(S) 1x1+ 1(S) 3x3+ 1(S) Dept hConcat Conv Conv Conv Conv 1x1+ 1(S) 3x3+ 1(S) 5x5+ 1(S) 1x1+ 1(S) Conv Conv MaxPool 1x1+ 1(S) 1x1+ 1(S) 3x3+ 1(S) AveragePool 5x5+ 3(V) Dept hConcat MaxPool 3x3+ 2(S) Conv Conv Conv Conv 1x1+ 1(S) 3x3+ 1(S) 5x5+ 1(S) 1x1+ 1(S) Conv Conv MaxPool 1x1+ 1(S) 1x1+ 1(S) 3x3+ 1(S) Dept hConcat Conv Conv Conv Conv 1x1+ 1(S) 3x3+ 1(S) 5x5+ 1(S) 1x1+ 1(S) Conv Conv MaxPool 1x1+ 1(S) 1x1+ 1(S) 3x3+ 1(S) Dept hConcat AveragePool 7x7+ 1(V) FC Conv 1x1+ 1(S) FC FC Soft maxAct ivat ion soft max0 Conv 1x1+ 1(S) FC FC Soft maxAct ivat ion soft max1 Soft maxAct ivat ion soft max2 GoogleNet, 22 layers (ILSVRC 2014) ILSVRC (ImageNet Large Scale Visual Recognition Challenge) AlexNet, VGG, GoogleNet, ResNet and more
  • 19. ResNet, 152 layers 1x1 conv, 64 3x3 conv, 64 1x1 conv, 256 1x1 conv, 64 3x3 conv, 64 1x1 conv, 256 1x1 conv, 64 3x3 conv, 64 1x1 conv, 256 1x2 conv, 128, /2 3x3 conv, 128 1x1 conv, 512 1x1 conv, 128 3x3 conv, 128 1x1 conv, 512 1x1 conv, 128 3x3 conv, 128 1x1 conv, 512 1x1 conv, 128 3x3 conv, 128 1x1 conv, 512 1x1 conv, 128 3x3 conv, 128 1x1 conv, 512 1x1 conv, 128 3x3 conv, 128 1x1 conv, 512 7x7 conv, 64, /2, pool/2 ResNet-152
  • 20. • Research dataset with >10 million images • Image annotated with labels from on ontology (>22K labels) • Generic images covering an extremely wide ranges of labels ImageNet dataset
  • 21. Pre-Built CNN from General Task on Millions of Images Output Layer Stripped Classi fier e.g. SVM dotted? Complex Objects & Scenes (people, animals, cars, beach scene, etc.) Low-Level Features (lines, edges, color fields, etc.) High-Level Features (corners, contours, simple shapes) Object Parts (wheels, faces, windows, etc.) Outputs of penultimate layer of ImageNet Trained CNN provide excellent general purpose image features
  • 22. Pre-Built CNN from General Task on Millions of Images Output Layer Stripped Using a pre-trained DNN, an accurate model can be achieved with thousands (or less) of labeled examples instead of millions dotted? Train one or more layers in new network
  • 23. Pre-trained Models http://bit.ly/2jf97NE http://bit.ly/2zNiN8B http://bit.ly/1KlVMf0 “Transferring knowledge” also possible in other domains such as use of word embeddings for text
  • 25. AI @ Scale Read Data Clean and Pre-process Train Models Inferencing @ Scale
  • 26. Distributed Training Architecture Data Parallelism Model Parallelism 1. Parallel training on different machines 2. Update the parameter server synchronously/asynchronously 3. Refresh the local model with new parameters, go to 1 and repeat 1. The global model is partitioned into K sub-models without overlap. 2. The sub-models are distributed over K local workers and serve as their local models. 3. In each mini-batch, the local workers compute the gradients of the local weights by back propagation. Credits: Taifeng Wang, DMTK team
  • 27. Selecting Big Data and AI Infrastructure Desktop / Laptop Spark Clusters CloudKubernetes Clusters
  • 29. What can we run on the deep learning infrastructure?
  • 30. Using Spark for Machine Learning • User needs to write lots of “glue” code to prepare features for ML algorithms. • Coerce types and data layout to that what’s expected by learner • Use different conventions for different learners • Lack of domain-specific libraries: computer vision or text analytics… • Latest: Image Data Support in Apache Spark 2.3 https://blogs.technet.microsoft.com/machinelearning/2018/03/05/image- data-support-in-apache-spark/ • Limited capabilities for model evaluation & model management
  • 31. Microsoft Machine Learning Library for Apache Spark (MMLSpark) GitHub Repo: https://github.com/Azure/mmlspark Get started now using Docker image: docker run -it -p 8888:8888 -e ACCEPT_EULA=yes microsoft/mmlspark Navigate to http://localhost:8888 to view example Jupyter notebooks
  • 32. Believe we can all do AI ☺5
  • 34. Discovering Your AI Super Powers - Tips And Tricks To Jumpstart Your AI Project Wee Hyong Tok, PhD Principal Data Science Manager Microsoft @weehyong Global Artificial Intelligence Conference 2018, Seattle Thank You!