introduction to deep learning (nvidia)
Post on 19-Mar-2017
1.396 Views
Preview:
TRANSCRIPT
1
Oct 2016
NVIDIA DEEP LEARNING
2
ENTERPRISE AUTOGAMING DATA CENTERPRO VISUALIZATION
THE WORLD LEADER IN VISUAL COMPUTING
3
THE BIG BANG IN MACHINE LEARNING
DNN GPUBIG DATA
100 hours of video uploaded every minute
350 millions images uploaded per day
2.5 Petabytes of customer data hourly
0.0
0.5
1.0
1.5
2.0
2.5
3.0
2008 2009 2010 2011 2012 2013 2014
NVIDIA GPU x86 CPU
TFLO
PS
4
BIG DATA & ANALYTICS
AUTOMOTIVEAuto sensors reporting
location, problems
COMMUNICATIONSLocation-based advertising
CONSUMER PACKAGED GOODSSentiment analysis of what’s hot, problems
$FINANCIAL SERVICES
Risk & portfolio analysis New products
EDUCATION & RESEARCHExperiment sensor analysis
HIGH TECHNOLOGY / INDUSTRIAL MFG.
Mfg. qualityWarranty analysis
LIFE SCIENCESClinical trials
MEDIA/ENTERTAINMENTViewers / advertising
effectiveness
ON-LINE SERVICES / SOCIAL MEDIA
People & career matching
HEALTH CAREPatient sensors, monitoring, EHRs
OIL & GASDrilling exploration sensor
analysis
RETAILConsumer sentiment
TRAVEL &TRANSPORTATION
Sensor analysis for optimal traffic flows
UTILITIESSmart Meter analysis for network capacity,
LAW ENFORCEMENT & DEFENSE
Threat analysis - social media monitoring, photo analysis
5
EXPONENTIAL DATA GROWTH
INCREASING DATA VARIETY
Search Marketing
Behavioral Targeting
Dynamic Funnels
User Generated Content
Mobile Web
SMS/MMS
Sentiment
HD Video
Speech To Text
Product/Service Logs
Social Network
Business Data Feeds
User Click Stream
Sensors Infotainment Systems
Wearable Devices
CyberSecurity Logs
ConnectedVehicles
Machine Data
IoT Data
Dynamic Pricing
Payment Record
Purchase Detail
Purchase Record
Support Contacts
Segmentation
Offer Details
Web Logs
Offer History
A/B Testing
BUSINESS PROCESS
PETA
BYTE
STE
RABY
TES
GIG
ABYT
ESEX
ABYT
ESZE
TTAB
YTES
Streaming Video
Natural Language Processing
WEB
DIGITAL
AI 90% of the world’s data created in the last year - IBM
6
7
WHAT IS DEEP LEARNING?
ARTIFICALINTELLIGENCE MACHINE
LEARNINGDEEP LEARNINGPerception
Reasoning
Planning
Optimization
Computational Statistics
Supervised and Unsupervised Learning
Neural networks
Distributed Representations
Hierarchical Explanatory Factors
Unsupervised Feature Engineering
8
DEEP LEARNING FUELING DISCOVERY
Classify Satellite Images for Carbon Monitoring
Analyze Obituaries on the Web for Cancer-related Discoveries
Determine Drug Treatments to Increase Child’s Chance of Survival
NASA AMES
9
DEEP LEARNING FOR EVERY APPLICATION
Visual search for e-commerce
Visual Search in Geoinformatics
Improving Agriculture: LettuceBot only
sprays weeds
10
Language Classification
Deep Learning CNN
Super-Human Language Translation
DEEP LEARNING FOR EVERY APPLICATION
11
DEEP LEARNING FOR EVERY APPLICATION
12
CONSUMERS LOVE DEEP LEARNING
13
MORE THAN 1,500 AI START UPS AROUND THE WORLD
Deep Learningfor Art
Deep Learning for Cybersecurity
Deep Learning for Genomics
Deep Learning for Self-Driving Cars
14
IMAGENET CHALLENGEWhere it all started … again
bird
frog
person
hammer
flower pot
power drill
person
car
helmet
motorcycle
person
dog
chair
1.2M training images • 1000 object categories
Challenge
15
ACHIEVING SUPERHUMAN PERFORMANCE
2012: Deep Learning researchers
worldwide discover GPUs
2016: Microsoft achieves speech recognition
milestone
2015: ImageNet — Deep Learning achievessuperhuman image
recognition
16
DEEP LEARNING ADOPTION IS EXPONENTIAL
# of Organizations Using Deep Learning
Source: Jeff Dean, Spark Summit 2016
17
MASSIVE COMPUTING CHALLENGE
SPEECH RECOGNITION
2014Deep Speech 1
80 GFLOP7,000 hrs of Data
~8% Error
465 GFLOP12,000 hrs of
Data~5% Error
2015Deep Speech 2
10XTraining Ops
IMAGE RECOGNITION
2012AlexNet
8 Layers1.4 GFLOP~16% Error
152 Layers22.6 GFLOP~3.5% Error
2015ResNet
16XModel
18
Device
NVIDIA DEEP LEARNING PLATFORM
TRAINING
DIGITS Training System
Deep Learning Frameworks
Tesla P100, DGX1
DATACENTER INFERENCING
DeepStream SDK
TensorRT
Tesla P40 & P4
19
Device
NVIDIA DEEP LEARNING PLATFORM
TRAINING DATACENTER INFERENCING
Training: comparing to Kepler GPU in 2013 using Caffe, Inference: comparing img/sec/watt to CPU: Intel E5-2697v4 using AlexNet
65Xin 3 years
Tesla P100
40Xvs CPU
Tesla P4
20
40x Efficient vs CPU, 8x Efficient vs FPGA
0
50
100
150
200
AlexNet
CPU FPGA 1x M4 (FP32) 1x P4 (INT8)
Imag
es/S
ec/W
att
Maximum Efficiency for Scale-out Servers
TESLA P4
5.5 TFLOPS
0
20,000
40,000
60,000
80,000
100,000
GoogLeNet AlexNet
8x M40 (FP32) 8x P40 (INT8)TESLA P40Highest Throughput for Scale-up Servers
Imag
es/S
ec
4x Boost in Less than One Year
21
INTRODUCING TESLA P100
Page Migration Engine
Virtually Unlimited Memory
CoWoS HBM2
3D Stacked Memory (i.e fast!)
NVLink
GPU Interconnect for Maximum Scalability
22
NVIDIA DGX-1AI Supercomputer-in-a-Box
170 TFLOPS | 8x Tesla P100 16GB | NVLink Hybrid Cube Mesh2x Xeon | 8 TB RAID 0 | Quad IB 100Gbps, Dual 10GbE | 3U — 3200W
23
Instant productivity — plug-and-play, supports every AI framework
Performance optimized across the entire stack
Always up-to-date via the cloud
Mixed framework environments —containerized
Direct access to NVIDIA experts
DGX STACKFully integrated Deep Learning platform
24
NVIDIA POWERS DEEP LEARNINGEvery major DL framework leverages NVIDIA SDKs
Mocha.jl
NVIDIA DEEP LEARNING SDK
COMPUTER VISION SPEECH & AUDIO NATURAL LANGUAGE PROCESSING
OBJECT DETECTION
IMAGE CLASSIFICATION
VOICE RECOGNITION
LANGUAGE TRANSLATION
RECOMMENDATION ENGINES
SENTIMENT ANALYSIS
25
NVIDIA DIGITSInteractive Deep Learning GPU Training System
Interactive deep neural network development environment for image classification and object detection
Schedule, monitor, and manage neural network training jobs
Analyze accuracy and loss in real time
Track datasets, results, and trained neural networks
Scale training jobs across multiple GPUs automatically
26
NVIDIA cuDNNAccelerating Deep Learning
High performance building blocks for deep learning frameworks
Drop-in acceleration for widely used deep learning frameworks such as Caffe, CNTK, Tensorflow, Theano, Torch and others
Accelerates industry vetted deep learning algorithms, such as convolutions, LSTM, fully connected, and pooling layers
Fast deep learning training performance tuned for NVIDIA GPUs
Deep Learning Training PerformanceCaffe AlexNet
Spee
d-up
of
Imag
es/S
ec v
s K4
0 in
201
3
K40 K80 + cuDN…
M40 + cuDNN4
P100 + cuDNN5
0x
10x
20x
30x
40x
50x
60x
70x
80x
“ NVIDIA has improved the speed of cuDNNwith each release while extending the interface to more operations and devices at the same time.”— Evan Shelhamer, Lead Caffe Developer, UC Berkeley
AlexNet training throughput on CPU: 1x E5-2680v3 12 Core 2.5GHz. 128GB System Memory, Ubuntu 14.04M40 bar: 8x M40 GPUs in a node, P100: 8x P100 NVLink-enabled
27
0 50 100 150 200 250 300
P40
P4
1x CPU (14 cores)
Inference Execution Time (ms)
11 ms
6 ms
User Experience: Instant Response45x Faster with Pascal + TensorRT
Faster, more responsive AI-powered services such as voice recognition, speech translation
Efficient inference on images, video, & other data in hyperscale production data centers
INTRODUCING NVIDIA TensorRTHigh Performance Inference Engine
260 ms
Training
Device
Datacenter
28
NVIDIA DEEPSTREAM SDKDelivering Video Analytics at Scale
Inference
PreprocessHardware Decode
“Boy playing soccer”
Simple, high performance API for analyzing video
Decode H.264, HEVC, MPEG-2, MPEG-4, VP9
CUDA-optimized resize and scale
TensorRT
0
20
40
60
80
100
1x Tesla P4 Server +DeepStream SDK
13x E5-2650 v4 Servers
Conc
urre
nt V
ideo
Str
eam
s
Concurrent Video Streams Analyzed
29
“Billions of intelligent devices will take advantage of deep learning to provide personalization and localization as GPUs become faster and faster over the next several years.” — Tractica
BILLIONS OF INTELLIGENT DEVICES
30
SMART CITIES OF THE FUTURE
“Pittsburgh's "predictive policing" program … police car laptops will display maps showing locations where crime is likely to occur, based on data-crunching algorithms developed by scientists at Carnegie Mellon University — Science
31
ACCELERATED ANALYTICS TECHNOLOGY
32
GPU-ACCELERATION HAS NO LIMITS
MapDMapD is 55x to 1,000x faster than comparable CPU databases on billion+ row datasets
KineticaHardware costs that are 1⁄10 that of standard in-memory databases
BlazeGraph200-300x speed-up
GraphistrySee 100x more data at millisecond speed
SQreamThe supercomputing powers of the GPU combined with SQream’s patented technology, results in up to 100 times faster analytics performance on terabyte-petabyte scale data sets
33
MASSIVE SCALE GPU ACCELERATED ANALYTICS
DEA theft of Silk Road bitcoinsSIEM attack escalationTwitter botnet deconstruction
34
GETTING STARTED WITH DEEP LEARNINGdeveloper.nvidia.com/deep-learning
35
Thank you!
top related