August 4, 1997: Skynet goes online August 29, 1997, 2:14am ET: - - PowerPoint PPT Presentation

▶
august 4 1997 skynet goes online august 29 1997 2 14am et
SMART_READER_LITE
LIVE PREVIEW

August 4, 1997: Skynet goes online August 29, 1997, 2:14am ET: - - PowerPoint PPT Presentation

Oct 22, 2022 120 likes •751 views

August 4, 1997: Skynet goes online August 29, 1997, 2:14am ET: Skynet gains consciousness August 29, 1997: Judgement Day Terminator (1984) What features does T-800 have? What features does T-800 have? Vision/Perception

slide-1
SLIDE 1
slide-2
SLIDE 2
slide-3
SLIDE 3

August 4, 1997: Skynet goes online

slide-4
SLIDE 4

August 29, 1997, 2:14am ET: Skynet gains ‘consciousness’

slide-5
SLIDE 5
slide-6
SLIDE 6
slide-7
SLIDE 7

August 29, 1997: Judgement Day

slide-8
SLIDE 8
slide-9
SLIDE 9
slide-10
SLIDE 10
slide-11
SLIDE 11
slide-12
SLIDE 12

Terminator (1984)

slide-13
SLIDE 13

What ‘features’ does T-800 have?

slide-14
SLIDE 14

What ‘features’ does T-800 have?

  • Vision/Perception
  • Speech
  • Motion/Planning
  • Object Manipulation
  • Self-Repair
  • Goal-directed Exploration
  • Social Skills
  • Ethics/Morality
slide-15
SLIDE 15

Back to our timeline..

slide-16
SLIDE 16

1960’s (1st Wave)

  • Single Layer networks
  • XOR problem killed research for two decades
slide-17
SLIDE 17

Mid-1980s (2nd Wave)

  • Multi-layer networks
  • Backpropagation algorithm
slide-18
SLIDE 18

2010s (3rd Wave)

  • Big Data

– O(M) labeled images

  • Big Compute
  • ‘Deep’ Learning
slide-19
SLIDE 19
  • 19 -
slide-20
SLIDE 20
slide-21
SLIDE 21

ImageNet Architecture

slide-22
SLIDE 22

Deep Learning for Computer Vision

slide-23
SLIDE 23
slide-24
SLIDE 24

Slide Courtesy of Nervana Systems

slide-25
SLIDE 25

Deep Learning for Segmentation

slide-26
SLIDE 26

Deep Learning for Caption Generation

slide-27
SLIDE 27

Deep Learning for Speech

slide-28
SLIDE 28

Google Assistant

slide-29
SLIDE 29
slide-30
SLIDE 30
slide-31
SLIDE 31
slide-32
SLIDE 32

IBM Watson

slide-33
SLIDE 33

IBM Project Debater

slide-34
SLIDE 34

DARPA Robotics Challenge

slide-35
SLIDE 35

MIT Cheetah

slide-36
SLIDE 36

Object Manipulation

slide-37
SLIDE 37

Object Manipulation

slide-38
SLIDE 38

DARPA Autonomous Driving Challenge

slide-39
SLIDE 39

Deep Learning for Self-Driving Cars

slide-40
SLIDE 40

Some Failures…

slide-41
SLIDE 41

Can Deep Learning Work for Science?

  • Similarities

– Tasks:

  • Pattern Classification
  • Regression
  • Clustering
  • Feature Learning
  • Anomaly Detection
  • Differences

– Unique attributes of Scientific Data

  • Multi-channel / Multi-variate
  • Double precision floating point
  • Noise and Artefacts
  • Statistics are likely different
slide-42
SLIDE 42

CAM5 0.25-degree simulation data

slide-43
SLIDE 43

Challenge: Multi-Variate Data

slide-44
SLIDE 44

Climate Science Tasks

  • 44-
slide-45
SLIDE 45

Logistic Regression K-Nearest Neighbor Support Vector Machine Random Forest ConvNet Test Test Test Test Test Tropical Cyclone 95.85 97.85 95.85 99.4 99.1 Atmospheric Rivers 82.65 81.7 83.0 88.4 90.0 Weather Fronts 89.8 76.45 90.2 87.5 89.4

Supervised Convolutional Architecture

slide-46
SLIDE 46

Semi-Supervised Convolutional Architecture (NIPS’17)

Encoder Decoder Classification + Bounding Box Regression Contributors: Evan Racah, Chris Pal, Chris Beckham, Samira Kahou, Tegan

  • Maharaj. MILA
slide-47
SLIDE 47

Classification + Regression Results

Ground Truth Prediction Contributors: Thorsten Kurth, Jian Yang, Ioannis Mitliagkas, Chris Pal, Nadathur Satish, Narayanan Sundaram, Amir Khosrowshahi, Michael Wehner, Bill Collins, Intel, Stanford, LBL, MILA.

slide-48
SLIDE 48

Deep Learning at 15PF (SC’17)

slide-49
SLIDE 49

Segmentation

Contributors: Mayur Mudigonda, Thorsten Kurth, Sean Treichler, Josh Romero, Massimiliano Fatica, Mike Houston. UC Berkeley, LBL, NVIDIA

slide-50
SLIDE 50

Segmentation Results

  • 50-
slide-51
SLIDE 51

Deep Learning for Science

Modeling galaxy shapes Oxford Nanopore sequencing Decoding speech from ECoG Generating cosmology mass maps Clustering Daya Bay events LHC Signal/Background classification

slide-52
SLIDE 52

Deep Learning Hardware

  • 52-
slide-53
SLIDE 53

Deep Learning Software

Technologies Deep Learning Frameworks Multi Node libraries Single Node libraries Hardware

MLSL MPI GRPC Neon, CNTK, MXNet, … CuDNN MKL-DNN CPUs (KNL) GPUs FPGAs Accelerators Horovod

slide-54
SLIDE 54

Open Challenges

  • 1. Performance and Scaling
  • 2. Complex Data
  • 3. Hyper-Parameter Optimization
  • 4. Scarcity of Labeled Data
  • 5. Interpretability and Visualization
  • 6. Theory
slide-55
SLIDE 55
slide-56
SLIDE 56

Assumptions…

  • Communities will self-organize and conduct labeling

campaigns

– Active Learning systems can determine optimal strategies for seeking labels

  • Incorporation of domain science principles into

learning algorithms

– Solution spaces that satisfy physical constraints

  • Pattern Classification, Clustering, Anomaly

Detection are solved problems

slide-57
SLIDE 57

What is the role of humans?

HPSS

/project

Labels Patterns, Clusters, Anomalies Mechanisms, Hypothesis

slide-58
SLIDE 58

How close are we to creating a T-800?

  • Vision/Percep,on ! " #
  • Speech " $ %
  • Mo,on/Planning ! $
  • Object Manipula,on &
  • Self-Repair ☹
  • Goal-directed Explora,on (
  • Social Skills )
  • Ethics/Morality *
slide-59
SLIDE 59

How about the T-1000 and T-X?

slide-60
SLIDE 60

Time Travel?

slide-61
SLIDE 61

Conclusions

  • AI appears to be working

– Genuine breakthroughs in vision, speech, control – Wide range of commercial applications

  • Tremendous potential for scientific applications

– Low-hanging fruit, but hard questions are coming next

  • NERSC is at the forefront of Deep Learning for

Science

– Applications – Hardware and Software – R&D on optimizations + scaling, methods

slide-62
SLIDE 62

Thanks!

  • Contact: prabhat@lbl.gov
  • Connect on LinkedIn
  • Internships, full-time opportunities