+ All Categories
Home > Documents > Making Sense of Artificial Intelligence: A Practical Guide · Artificial Intelligence Machine...

Making Sense of Artificial Intelligence: A Practical Guide · Artificial Intelligence Machine...

Date post: 27-Jul-2018
Category:
Upload: dinhphuc
View: 234 times
Download: 0 times
Share this document with a friend
15
Making Sense of Artificial Intelligence: A Practical Guide JEDEC Mobile & IOT Forum Copyright © 2018 Young Paik, Samsung Senior Director Product Planning
Transcript
Page 1: Making Sense of Artificial Intelligence: A Practical Guide · Artificial Intelligence Machine Learning Deep Learning ... How would you implement mobile speech recognition? Find New

Making Sense of Artificial Intelligence:A Practical Guide

JEDEC Mobile

& IOT Forum

Copyright © 2018 Young Paik,Samsung Senior Director Product Planning

Page 2: Making Sense of Artificial Intelligence: A Practical Guide · Artificial Intelligence Machine Learning Deep Learning ... How would you implement mobile speech recognition? Find New

Disclaimer

• This presentation and/or accompanying oral statements by Samsung representatives collectively, the “Presentation”) is intended to provide information concerning the SSD and memory industry and Samsung Electronics Co., Ltd. and certain affiliates (collectively, “Samsung”). While Samsung strives to provide information that is accurate and up-to-date, this Presentation may nonetheless contain inaccuracies or omissions. As a consequence, Samsung does not in any way guarantee the accuracy or completeness of the information provided in this Presentation.

• This Presentation may include forward-looking statements, including, but not limited to, statements about any matter that is not a historical fact; statements regarding Samsung’s intentions, beliefs or current expectations concerning, among other things, market prospects, technological developments, growth, strategies, and the industry in which Samsung operates; and statements regarding products or features that are still in development. By their nature, forward-looking statements involve risks and uncertainties, because they relate to events and depend on circumstances that may or may not occur in the future. Samsung cautions you that forward looking statements are not guarantees of future performance and that the actual developments of Samsung, the market, or industry in which Samsung operates may differ materially from those made or suggested by the forward-looking statements in this Presentation. In addition, even if such forward-looking statements are shown to be accurate, those developments may not be indicative of developments in future periods.

2

Page 3: Making Sense of Artificial Intelligence: A Practical Guide · Artificial Intelligence Machine Learning Deep Learning ... How would you implement mobile speech recognition? Find New

Deep Learning Has Changed AI

Artificial

Intelligence

Machine

Learning

Deep Learning

Data DrivenRules Based

Not accurate enough to be

commercially viableApproaching Human

Level Accuracy

Example: Speech recognitionFew words ~ 99% accurate

Many words ~ 60% accurate

Page 4: Making Sense of Artificial Intelligence: A Practical Guide · Artificial Intelligence Machine Learning Deep Learning ... How would you implement mobile speech recognition? Find New

This Is Not That Kind of Talk

Stochastic Gradient Descent

Backpropagation

Variable precision math

Deep Neural Net

Convolutional Neural NetRecurrent Neural Net

LSTM

Softmax

Pooling

ReLu

Supervised Training

Deep Learning has a lot of jargon…

This talk will skip as much as possible.

Fully connected

GPU

CUDA

OpenCL

Page 5: Making Sense of Artificial Intelligence: A Practical Guide · Artificial Intelligence Machine Learning Deep Learning ... How would you implement mobile speech recognition? Find New

High-Level AI Flow

Data

Storage

Data

Processing

DL Model

Deployment

SSD

DDR

GDDR

HBM

Mobile CPU

NPU

LPDDRGPU Memory

Many TB - PB+

>1 TBps BW

Deep Learning Simplified

< 1 MB – 10 GB

Phones AIAssistants

HomeDevices IoT

Auto

Training Inference

Hours - Weeks

Page 6: Making Sense of Artificial Intelligence: A Practical Guide · Artificial Intelligence Machine Learning Deep Learning ... How would you implement mobile speech recognition? Find New

3 Takeaways

�Data is King

More data = more accuracy

�Deep Learning is hard

Leave it to the professionals

�You don’t have to use one AI

Many, smaller AIs are better than one big one

Page 7: Making Sense of Artificial Intelligence: A Practical Guide · Artificial Intelligence Machine Learning Deep Learning ... How would you implement mobile speech recognition? Find New

Circle of (DL) Life

DL models need to be constantly be fed data.

When designing new products find ways to feed back data to improve AIs.

Gather Data

Create AI

DeployExample:

Home thermostat:User override of settings should be

seen as an AI fault and feed back.

Page 8: Making Sense of Artificial Intelligence: A Practical Guide · Artificial Intelligence Machine Learning Deep Learning ... How would you implement mobile speech recognition? Find New

Real World Considerations

Data Training DL Model

Network Device

Server

Training DurationTraining may take days or even weeks. Hard to parallelize.

DL Model SizeIn general, larger models are more accurate, but may be hard to fit on mobile/IoT devices.

LatencyKeeping models on servers will increase latency.

PrivacyConstantly feeding data back to servers may have privacy concerns.

PowerConstantly running DNNs on devices may take a lot of power.

BandwidthEnd users may not want to constantly use bandwidth to servers.

ComputeMobile/IoT resources may not be enough to run on-device.

DL Model on-device

DL Model on-server

Decentralized DBSome apps require additional data that are best centrally stored.

Q: How would you implement mobile speech recognition?

Page 9: Making Sense of Artificial Intelligence: A Practical Guide · Artificial Intelligence Machine Learning Deep Learning ... How would you implement mobile speech recognition? Find New

Tricks For Improvement

Transfer Learning Model Compressions

Take a pre-trained DL model and retrain it with new data.

Pros• Trains much faster

than first model.

• No need for AI

scientist.

• Easy frameworks

available in cloud.

Cons• Use case must be

very similar.

• Not as accurate as

original.

Pros• DL models may

compress by 500x.

• Accuracy may not be

impacted.

• May decrease power

needed to infer.

Cons• Requires additional

processing after

initial training.

Many weights and nodes may not be important and can be removed.

Page 10: Making Sense of Artificial Intelligence: A Practical Guide · Artificial Intelligence Machine Learning Deep Learning ... How would you implement mobile speech recognition? Find New

Real World Considerations

Data Training DL Model

Network Device

Server

Training DurationTraining may take days or even weeks. Hard to parallelize.

DL Model SizeIn general, larger models are more accurate, but may be hard to fit on mobile/IoT devices.

LatencyKeeping models on servers will increase latency.

PrivacyConstantly feeding data back to servers may have privacy concerns.

PowerConstantly running DNNs on devices may take a lot of power.

BandwidthEnd users may not want to constantly use bandwidth to servers.

ComputeMobile/IoT resources may not be enough to run on-device.

DL Model on-device

DL Model on-server

Decentralized DBSome apps require additional data that are best centrally stored.

Q: How would you implement mobile speech recognition?

Page 11: Making Sense of Artificial Intelligence: A Practical Guide · Artificial Intelligence Machine Learning Deep Learning ... How would you implement mobile speech recognition? Find New

Find New Ways Of Using Old Tech

Artificial

Intelligence

Machine

Learning

Deep Learning

Data DrivenRules Based

New uses?Approaching Human

Level Accuracy

Example: Speech recognitionFew words ~ 99% accurateMany words ~ 60% accurate

Page 12: Making Sense of Artificial Intelligence: A Practical Guide · Artificial Intelligence Machine Learning Deep Learning ... How would you implement mobile speech recognition? Find New

Making Use of Multiple AIs

Data Training Model

Server

Network Device

PowerSpecialized AI for hotwordsrequire much less power.

Privacy and BandwidthUse of hotword minimizes data sent back to server.

LatencyLatency for full AI is still longer, but now hotword recognition masks issue.

Decentralized DBCentralized DB can store data that can be used by AI.

“HOTWORD, What is …”“What is …”

Page 13: Making Sense of Artificial Intelligence: A Practical Guide · Artificial Intelligence Machine Learning Deep Learning ... How would you implement mobile speech recognition? Find New

Other Use Cases

Data Training DL Model

Network Device

Server

DL Model on-device

DL Model on-server

Q: How would you implement …

Autonomous Driving?

Security Cameras?Facial

Recognition?

Drone Delivery

Page 14: Making Sense of Artificial Intelligence: A Practical Guide · Artificial Intelligence Machine Learning Deep Learning ... How would you implement mobile speech recognition? Find New

Conclusions

• AI is still early in its development.

• Design of AI systems is evolving.

• You may find new uses for old ideas.

Page 15: Making Sense of Artificial Intelligence: A Practical Guide · Artificial Intelligence Machine Learning Deep Learning ... How would you implement mobile speech recognition? Find New

Thank you!

Young [email protected]


Recommended