Tutorial on Methods for Interpreting and Understanding Deep Neural - - PowerPoint PPT Presentation

tutorial on methods for interpreting and understanding
SMART_READER_LITE
LIVE PREVIEW

Tutorial on Methods for Interpreting and Understanding Deep Neural - - PowerPoint PPT Presentation

Tutorial on Methods for Interpreting and Understanding Deep Neural Networks Wojciech Samek Grgoire Montavon Klaus-Robert Mller (Fraunhofer HHI) (TU Berlin) (TU Berlin) 1:30 - 2:00 Part 1: Introduction 2:00 - 3:00 Part 2a: Making Deep


slide-1
SLIDE 1

ICASSP 2017 Tutorial — W. Samek, G. Montavon & K.-R. Müller

Tutorial on Methods for Interpreting and Understanding Deep Neural Networks

Wojciech Samek (Fraunhofer HHI) Grégoire Montavon (TU Berlin) Klaus-Robert Müller (TU Berlin) 1:30 - 2:00 Part 1: Introduction 2:00 - 3:00 Part 2a: Making Deep Neural Networks Transparent 3:00 - 3:30 Break 3:30 - 4:00 Part 2b: Making Deep Neural Networks Transparent 4:00 - 5:00 Part 3: Applications & Discussion

slide-2
SLIDE 2

ICASSP 2017 Tutorial — W. Samek, G. Montavon & K.-R. Müller /29

Before we start

Alexander Binder (SUTD) Sebastian Lapuschkin (Fraunhofer HHI) We thank our collaborators ! Lecture notes will be online soon at: Please ask questions at any time !

slide-3
SLIDE 3

ICASSP 2017 Tutorial — W. Samek, G. Montavon & K.-R. Müller

  • W. Samek, G. Montavon, K.-R. Müller

Tutorial on Methods for Interpreting and Understanding Deep Neural Networks Part 1: Introduction

slide-4
SLIDE 4

ICASSP 2017 Tutorial — W. Samek, G. Montavon & K.-R. Müller /29 4

Recent ML Systems achieve superhuman Performance

AlphaGo beats Go human champ Deep Net outperforms humans in image classification Deep Net beats human at recognizing traffic signs DeepStack beats professional poker players Computer out-plays humans in "doom" Autonomous search-and-rescue drones outperform humans IBM's Watson destroys humans in jeopardy

slide-5
SLIDE 5

ICASSP 2017 Tutorial — W. Samek, G. Montavon & K.-R. Müller /29 5

From Data to Information

Computing power Deep Nets / Kernel Machines / … Information (implicit) Solve task Huge volumes of data Interpretable Information extract

slide-6
SLIDE 6

ICASSP 2017 Tutorial — W. Samek, G. Montavon & K.-R. Müller /29 6

From Data to Information

ResNet (3.57%) GoogleNet (6.7%) VGG (7.3%) AlexNet (16.4%) Performance Clarifai (11.1%) Interpretability

Information Data Interpretable for human

Crucial in many applications (industry, sciences …)

slide-7
SLIDE 7

ICASSP 2017 Tutorial — W. Samek, G. Montavon & K.-R. Müller /29 “global explanation” “individual explanation” 7

Interpretable vs. Powerful Models ?

Linear model Non-linear model vs. Poor fit, but easily interpretable Can be very complex

slide-8
SLIDE 8

ICASSP 2017 Tutorial — W. Samek, G. Montavon & K.-R. Müller /29 “global explanation” “individual explanation” 8

Interpretable vs. Powerful Models ?

Linear model Non-linear model vs. Poor fit, but easily interpretable Can be very complex

60 million parameters 650,000 neurons We have techniques to interpret and explain such complex models !

slide-9
SLIDE 9

ICASSP 2017 Tutorial — W. Samek, G. Montavon & K.-R. Müller /29 9

train best model interpret it train interpretable model

suboptimal or biased due to assumptions (linearity, sparsity …)

vs.

Interpretable vs. Powerful Models ?

slide-10
SLIDE 10

ICASSP 2017 Tutorial — W. Samek, G. Montavon & K.-R. Müller /29

Dimensions of Interpretability

model prediction data

“Explain why a certain pattern x has been classified in a certain way f(x).” “What would a pattern belonging to a certain category typically look like according to the model.” “Which dimensions of the data are most relevant for the task.”

Different dimensions

  • f “interpretability”

10

prediction model

“Explain why a certain pattern x has been classified in a certain way f(x).” “What would a pattern belonging to a certain category typically look like according to the model.”

slide-11
SLIDE 11

ICASSP 2017 Tutorial — W. Samek, G. Montavon & K.-R. Müller /29

Why Interpretability ?

Wrong decisions can be costly and dangerous 1) Verify that classifier works as expected

11

“Autonomous car crashes, because it wrongly recognizes …” “AI medical diagnosis system misclassifies patient’s disease …”

slide-12
SLIDE 12

ICASSP 2017 Tutorial — W. Samek, G. Montavon & K.-R. Müller /29

2) Improve classifier

12

Why Interpretability ?

Generalization error Generalization error + human experience

slide-13
SLIDE 13

ICASSP 2017 Tutorial — W. Samek, G. Montavon & K.-R. Müller /29

“It's not a human move. I've never seen a human play this move.” (Fan Hui) 3) Learn from the learning machine Old promise: “Learn about the human brain.”

13

Why Interpretability ?

slide-14
SLIDE 14

ICASSP 2017 Tutorial — W. Samek, G. Montavon & K.-R. Müller /29 14

4) Interpretability in the sciences Stock market analysis: “Model predicts share value with __% accuracy.” In medical diagnosis: “Model predicts that X will survive with probability __” What to do with this information ? Great !!!

Why Interpretability ?

slide-15
SLIDE 15

ICASSP 2017 Tutorial — W. Samek, G. Montavon & K.-R. Müller /29 15

4) Interpretability in the sciences Learn about the physical / biological / chemical mechanisms. (e.g. find genes linked to cancer, identify binding sites …)

Why Interpretability ?

slide-16
SLIDE 16

ICASSP 2017 Tutorial — W. Samek, G. Montavon & K.-R. Müller /29

European Union’s new General Data Protection Regulation

16

5) Compliance to legislation “right to explanation” “With interpretability we can ensure that ML models work in compliance to proposed legislation.” Retain human decision in order to assign responsibility.

Why Interpretability ?

slide-17
SLIDE 17

ICASSP 2017 Tutorial — W. Samek, G. Montavon & K.-R. Müller /29

Interpretability as a gateway between ML and society

  • Make complex models acceptable for certain applications.
  • Retain human decision in order to assign responsibility.
  • “Right to explanation”

Interpretability as powerful engineering tool

  • Optimize models / architectures
  • Detect flaws / biases in the data
  • Gain new insights about the problem
  • Make sure that ML models behave “correctly”

17

Why Interpretability ?

slide-18
SLIDE 18

ICASSP 2017 Tutorial — W. Samek, G. Montavon & K.-R. Müller /29

Techniques of Interpretation

18

slide-19
SLIDE 19

ICASSP 2017 Tutorial — W. Samek, G. Montavon & K.-R. Müller /29

Interpreting models (ensemble)

19

Explaining decisions (individual)

  • find prototypical example of a category
  • find pattern maximizing activity of a neuron
  • “why” does the model arrive at this

particular prediction

  • verify that model behaves as expected

crucial for many practical applications

Techniques of Interpretation

better understand internal representation

slide-20
SLIDE 20

ICASSP 2017 Tutorial — W. Samek, G. Montavon & K.-R. Müller /29

In medical context

  • Population view (ensemble)
  • Which symptoms are most common for the disease
  • Which drugs are most helpful for patients
  • Patient’s view (individual)
  • Which particular symptoms does the patient have
  • Which drugs does he need to take in order to recover

Both aspects can be important depending on who you are (FDA, doctor, patient).

20

Techniques of Interpretation

slide-21
SLIDE 21

ICASSP 2017 Tutorial — W. Samek, G. Montavon & K.-R. Müller /29

Interpreting models

21

  • find prototypical example of a category
  • find pattern maximizing activity of a neuron

Techniques of Interpretation

goose cheeseburger car

slide-22
SLIDE 22

ICASSP 2017 Tutorial — W. Samek, G. Montavon & K.-R. Müller /29

Interpreting models

22

  • find prototypical example of a category
  • find pattern maximizing activity of a neuron

Techniques of Interpretation

goose cheeseburger car simple regularizer (Simonyan et al. 2013)

slide-23
SLIDE 23

ICASSP 2017 Tutorial — W. Samek, G. Montavon & K.-R. Müller /29

Interpreting models

23

  • find prototypical example of a category
  • find pattern maximizing activity of a neuron

Techniques of Interpretation

goose cheeseburger car complex regularizer (Nguyen et al. 2016)

slide-24
SLIDE 24

ICASSP 2017 Tutorial — W. Samek, G. Montavon & K.-R. Müller /29 24

Explaining decisions

  • “why” does the model arrive at a certain prediction
  • verify that model behaves as expected

Techniques of Interpretation

slide-25
SLIDE 25

ICASSP 2017 Tutorial — W. Samek, G. Montavon & K.-R. Müller /29 25

Explaining decisions

  • “why” does the model arrive at a certain prediction
  • verify that model behaves as expected

Techniques of Interpretation

  • Sensitivity Analysis
  • Layer-wise Relevance Propagation (LRP)
slide-26
SLIDE 26

ICASSP 2017 Tutorial — W. Samek, G. Montavon & K.-R. Müller /29 26

Techniques of Interpretation

Sensitivity Analysis (Simonyan et al. 2014)

slide-27
SLIDE 27

ICASSP 2017 Tutorial — W. Samek, G. Montavon & K.-R. Müller /29 27

Techniques of Interpretation

Layer-wise Relevance Propagation (LRP) (Bach et al. 2015)

Theoretical interpretation Deep Taylor Decomposition (Montavon et al., 2017)

“every neuron gets it’s share of relevance depending on activation and strength of connection.”

slide-28
SLIDE 28

ICASSP 2017 Tutorial — W. Samek, G. Montavon & K.-R. Müller /29 28

Techniques of Interpretation Techniques of Interpretation

“what makes this image less / more ‘scooter’ ?” “what makes this image ‘scooter’ at all ?”

LRP / Taylor Decomposition: Sensitivity Analysis:

slide-29
SLIDE 29

ICASSP 2017 Tutorial — W. Samek, G. Montavon & K.-R. Müller /29

More to come

Part 2 Part 2

quality of explanations, applications, interpretability in the sciences, discussion

29

Part 3