Download presentation

Presentation is loading. Please wait.

Published byOdalys Alltop Modified over 2 years ago

1
Teaching Machines to Learn by Metaphors Omer Levy & Shaul Markovitch Technion – Israel Institute of Technology

3
Concept Learning by Induction

4
Few Examples

5
Transfer Learning Target (New) Source (Original)

6
Define: Related Concept

7
Transfer Learning Approaches Common Inductive Bias Common Instances Common Features

8
Different Feature Space

9
Example 023-3-2

10
Example 023-3-2 0 49

11
Example 023-3-2 0 49

12
Common Inductive Bias 023-3-2 0 49

13
Common Inductive Bias 023-3-2 0 49

14
Common Instances 023-3-2 0 49

15
Common Features 2 3 -3 -2 49

16
New Approach to Transfer Learning

17
Our Solution: Metaphors

18
Metaphors Target (New) Source (Original)

19
Concept Learner Metaphor Learner Source Target +/-

22
Theorem

23
The Metaphor Theorem

24
Redefine Transfer Learning

26
Metaphor Learning Framework

27
Concept Learning Framework Search Algorithm Hypothesis Space Evaluation Function Data

28
Source Target Metaphor Learning Framework Search Algorithm Metaphor Space Evaluation Function

29
Metaphor Evaluation

36
Metaphor Spaces

37
General Few Degrees of Freedom Representation-Specific Bias

38
Geometric Transformations ЯR

39
Dictionary-Based Metaphors cheesequeso

40
Linear Transformations

41
Which metaphor space should I use?

42
Automatic Selection of Metaphor Spaces Which metaphor space should I use?

43
Occam’s Razor Automatic Selection of Metaphor Spaces Which metaphor space should I use?

44
Structural Risk Minimization Occam’s Razor Automatic Selection of Metaphor Spaces Which metaphor space should I use?

45
Automatic Selection of Metaphor Spaces

48
Empirical Evaluation

49
Reference Methods Baseline Target Only Identity Metaphor Merge State-of-the-Art Frustratingly Easy Domain Adaptation – Daumé, 2007 MultiTask Learning – Caruana, 1997; Silver et al, 2010 TrAdaBoost – Dai et al, 2007

50
Digits: Negative Image

53
Digits: Higher Resolution

56
Wine

58
Qualitative Results Transfer Learning Task Target Instance Target Sample Size 12510 Digits: Negative Image Digits: Higher Resolution

59
Discussion

60
Recap Problem: Concept learning with few examples Solution: Metaphors

61
Recap

65
What if the concepts are not related?

67
Metaphors are not a measure of relatedness

68
Metaphors are not a measure of relatedness Metaphors explain how concepts are related

69
Vision

71
Explaining how concepts are related since 2012. M E T A P H O R S

72
Concept Learning by Induction

74
Few Examples

76
Approaches Explanation-Based Learning Semi-Supervised Learning Transfer Learning

77
Explanation-Based Learning Axioms Data Logical Deduction

78
Semi-Supervised Learning

79
Transfer Learning

80
Target (New) Source (Original)

81
Transfer Learning

82
Target (New) Source (Original)

83
Define: Related Concept

84
Transfer Learning Approaches Common Inductive Bias Common Instances Common Features

85
Common Inductive Bias

88
Common Instances

93
Common Features 1.Perform feature selection on source 2.Use that selection on target

94
Which definition is better?

95
Different Feature Space

96
Example 023-3-2

97
Example 023-3-2 0 49

98
Example 023-3-2 0 49

99
Common Inductive Bias 023-3-2 0 49

100
Common Inductive Bias 023-3-2 0 49

101
Common Instances 023-3-2 0 49

102
Common Features 2 3 -3 -2 49

103
Our Solution: Metaphors

104
Performance with Automatic Selection of Metaphor Spaces Digits: Negative Image

105
Performance with Automatic Selection of Metaphor Spaces Digits: Negative Image Geometric Transformations Feature Reordering Orthogonal Linear Transformations Orthogonal Quadratic Transformations

106
Performance with Automatic Selection of Metaphor Spaces Digits: Negative Image Geometric Transformations Feature Reordering Orthogonal Linear Transformations Orthogonal Quadratic Transformations

108
What if I have more than one source?

109
Multiple Source Datasets B Я HRZ

110
B Я H R Z

111
Я R

112
Performance with Multiple Source Datasets Latin & Cyrillic

113
Performance with Multiple Source Datasets Latin & Cyrillic ABCDEFG HIJKLMN OPQRSTU VWXYZ

114
Performance with Multiple Source Datasets Latin & Cyrillic ABCDEFG HIJKLMN OPQRSTU VWXYZ

115
Performance with Multiple Source Datasets

Similar presentations

OK

A Survey on Transfer Learning Sinno Jialin Pan Department of Computer Science and Engineering The Hong Kong University of Science and Technology Joint.

A Survey on Transfer Learning Sinno Jialin Pan Department of Computer Science and Engineering The Hong Kong University of Science and Technology Joint.

© 2017 SlidePlayer.com Inc.

All rights reserved.

Ads by Google

Ppt on current account deficit in australia Ppt on a secure crypto biometric verification protocol Ppt on culture heritage of india Ppt on marketing in hindi Ppt on polynomials in maths what does the range Ppt on educating girl child Ppt on brand equity Ppt on hydro power plant Ppt on double input z-source dc-dc converter Doc convert to ppt online ticket