Beruflich Dokumente
Kultur Dokumente
Andrew Ng
Andrew Ng
Virtuous circle of AI
Great product
AI!
Data Users
Andrew Ng
Data and machine learning
New AI methods
Performance!
(deep learning)
Most learning
algorithms
Amount of data!
Andrew Ng
Virtuous circle of AI
Great product
AI!
Data Users
Andrew Ng
Deep Learning
Andrew Ng
STanford AI Robot (STAIR)
Andrew Ng
Computer vision: Identify coffee mug
Andrew Ng
Computer vision: Identify coffee mug
Mug Mug
Mug
Mug
Mug
Mug
Mug
Andrew Ng
Why is computer vision hard?
Andrew Ng
Computer vision
Learning
algorithm
Andrew Ng
Computer vision
Feature Learning
representation algorithm
Andrew Ng
Features for vision
Andrew Ng
Features for machine learning
Images!
Audio!
Andrew Ng
Features for audio
Andrew Ng
Features for text
Andrew Ng
The idea:
Andrew Ng
The idea:
Andrew Ng
The one learning algorithm hypothesis
Auditory Cortex
Andrew Ng
The one learning algorithm hypothesis
Somatosensory Cortex
Andrew Ng
Neurons in the brain
Andrew Ng
Neural Network (Deep Learning)
x1
x2
Output
x3
Layer L4
x4
Layer L3
Layer L1 Layer L2
Andrew Ng
Deep Learning trends
Now
Andrew Ng
Learning from tagged data (supervised)
Coffee mug
Coffee mug Coffee mug
Andrew Ng
Bigger is better
Performance
Andrew Ng
AI as a computer systems problem
10 million connec+ons
1 billion connec+ons
Andrew Ng
Speech recognition, and more.
Andrew Ng
Deep Learning applications
Andrew Ng
Tagged vs. untagged data
Coffee mug
Coffee mug Coffee mug
Andrew Ng
Untagged data (unsupervised learning)
Andrew Ng
How does the brain process images?
Andrew Ng
Start with Image patches
50
100
150
200
250
300
350 R14 x 14
400
450
500
50 100 150 200 250 300 350 400 450 500
Andrew Ng
! Sparse Coding
!
Andrew Ng
Sparse Coding
1, 2, , 64!
Test example
Andrew Ng
Comparing to Biology
[Evan Smith]
Andrew Ng
Comparing to Biology
[Evan Smith]
Andrew Ng
Learning from YouTube videos
Andrew Ng
Face neuron
Andrew Ng
Cat neuron
Andrew Ng
Deep Learning
object models!
object parts!
edges!
pixels!
Andrew Ng
16,000 CPUs is expensive
Andrew Ng
GPUs (Graphics Processor Unit)
Andrew Ng
Building huge neural networks
10 million connec+ons
1 billion connec+ons
10 billion connec+ons
Deep learning
Performance!
Older
algorithms
Amount of data!
Andrew Ng
Highway perception
Andrew Ng
Deep Learning trends
Andrew Ng
Untagged data and AI (unsupervised learning)
Andrew Ng
Computer vision (~6 years)
Feature
extraction! Prediction! Combine!
(SIFT)! (SVM)! (Maxpool)!
Deep Learning Deep Learning
Deep Learning
Andrew Ng
Speech recognition (next 2-3 years?)
Acoustic Language
model! Inference!
model!
(GMM)! (HMM)!
(ngram)!
Deep Learning Deep Learning
Deep Learning
Andrew Ng
AI will transform the internet
Andrew Ng
Speech Images
Andrew Ng
Speech
recogni+on
Andrew Ng
Baidu Cool Box
Andrew Ng
Andrew Ng
35.5% 15.8%
Andrew Ng
Baidu
Encyclopedia
Encyclopedia
Hyacinth
Flower shop
Andrew Ng
Image queries
Andrew Ng
Baidu Eye
Andrew Ng
Andrew Ng
Smart
glasses
designs
Andrew Ng
Extending
human
percep+on
Andrew Ng
Extending
human
percep+on
Andrew Ng
Comparison
to
smart
glasses
designs
Andrew Ng
Speech Images Text
Andrew Ng
From Control to Perception
Andrew Ng
Stanfords PR-1 robot
[Ken Andrew
Salisbury]
Ng
AI will transform the internet
Technology areas with potential for paradigm shift:
Computer vision
Speech recognition & speech synthesis
Language understanding: Machine translation;
Web search; Dialog systems; .
Advertising
Personalization/recommendation systems
Robotics
All this is hard: scalability, algorithms.
Andrew Ng
Virtuous circle of AI
Great product
AI!
Data Users
Andrew Ng
The AI mission
Andrew Ng
Thank you.
Tutorial: deeplearning.stanford.edu
Andrew Ng
END END
END END
Andrew Ng
Discussion:
Engineering vs. Data
Contribution to performance!
Human! Data/!
ingenuity! learning!
Andrew Ng
Discussion:
Engineering vs. Data
Contribution to performance!
Time!
Now!
Andrew Ng
Correctly found mug Mistake
Andrew Ng
Correctly found mug Mistake
Andrew Ng
Correctly found mug Mistake
Andrew Ng
Correctly found mug Mistake
Andrew Ng