Teaching Machines to Learn by Metaphors at Technion Israel Institute of Technology
Teaching Machines to Learn by
Metaphors
Omer Levy & Shaul Markovitch
Technion – Israel Institute of Technology
Concept Learning by Induction
Few Examples
Transfer Learning
Target
(New)
Source
(Original)
Define:
Related Concept
Transfer Learning Approaches
•
Common Inductive Bias
•
Common Instances
•
Common Features
Different Feature Space
Example
0
2
3
-3
-2
Example
0
2
3
-3
-2
0
4
9
Example
0
2
3
-3
-2
0
4
9
Common Inductive Bias
0
2
3
-3
-2
0
4
9
Common Inductive Bias
0
2
3
-3
-2
0
4
9
Common Instances
0
2
3
-3
-2
0
4
9
Common Features
2
3
-3
-2
4
9
New Approach to Transfer Learning
Our Solution:
Metaphors
Metaphors
Target
(New)
Source
(Original)
Concept
Learner
Metaphor
Learner
Source
Target
+/-
Theorem
The
Metaphor
Theorem
Redefine Transfer Learning
Redefine Transfer Learning
Metaphor Learning Framework
Concept Learning Framework
Search
Algorithm
Hypothesis
Space
Evaluation
Function
Data
Source
Target
Metaphor Learning Framework
Search
Algorithm
Metaphor
Space
Evaluation
Function
Metaphor Evaluation
Metaphor Evaluation
Metaphor Evaluation
Metaphor Evaluation
Metaphor Evaluation
Metaphor Evaluation
Metaphor Evaluation
Metaphor Spaces
Metaphor Spaces
•
General
•
Few Degrees of Freedom
•
Representation-Specific Bias
Geometric Transformations
Я
R
Dictionary-Based Metaphors
cheese
queso
Linear Transformations
Which metaphor space should I use?
Automatic Selection of Metaphor Spaces
Which metaphor space should I use?
Occam’s Razor
Automatic Selection of Metaphor Spaces
Which metaphor space should I use?
Structural Risk Minimization
Occam’s Razor
Automatic Selection of Metaphor Spaces
Which metaphor space should I use?
Automatic Selection of Metaphor Spaces
Automatic Selection of Metaphor Spaces
Automatic Selection of Metaphor Spaces
Empirical Evaluation
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
Digits: Negative Image
Digits: Negative Image
Digits: Negative Image
Digits: Higher Resolution
Digits: Higher Resolution
Digits: Higher Resolution
Wine
Wine
Qualitative Results
Discussion
Recap
•
Problem: Concept learning with few examples
•
Solution:
Metaphors
Recap
Recap
Recap
Recap
What if the concepts are
not
related?
What if the concepts are
not
related?
Metaphors are
not
a measure of relatedness
Metaphors are
not
a measure of relatedness
Metaphors explain
how
concepts are related
Vision
Explaining
how
concepts are related since 2012.
M
E T A P H O R
S
Concept Learning by Induction
Concept Learning by Induction
Few Examples
Few Examples
Approaches
•
Explanation-Based Learning
•
Semi-Supervised Learning
•
Transfer Learning
Explanation-Based Learning
Axioms
Data
Logical
Deduction
Semi-Supervised Learning
Transfer Learning
Transfer Learning
Target
(New)
Source
(Original)
Transfer Learning
Transfer Learning
Target
(New)
Source
(Original)
Define:
Related Concept
Transfer Learning Approaches
•
Common Inductive Bias
•
Common Instances
•
Common Features
Common Inductive Bias
Common Inductive Bias
Common Inductive Bias
Common Instances
Common Instances
Common Instances
Common Instances
Common Instances
Common Features
1.
Perform feature selection on
source
2.
Use that selection on
target
Which definition is better?
Different Feature Space
Example
0
2
3
-3
-2
Example
0
2
3
-3
-2
0
4
9
Example
0
2
3
-3
-2
0
4
9
Common Inductive Bias
0
2
3
-3
-2
0
4
9
Common Inductive Bias
0
2
3
-3
-2
0
4
9
Common Instances
0
2
3
-3
-2
0
4
9
Common Features
2
3
-3
-2
4
9
Our Solution:
Metaphors
Performance with Automatic Selection
of Metaphor Spaces
Digits: Negative Image
Performance with Automatic Selection
of Metaphor Spaces
Digits: Negative Image
•
Geometric Transformations
•
Feature Reordering
•
Orthogonal Linear Transformations
•
Orthogonal Quadratic Transformations
Performance with Automatic Selection
of Metaphor Spaces
Digits: Negative Image
•
Geometric Transformations
•
Feature Reordering
•
Orthogonal Linear Transformations
•
Orthogonal Quadratic Transformations
What if I have more than one
source
?
Multiple Source Datasets
B
Я
H
R
Z
Multiple Source Datasets
B
Я
H
R
Z
Multiple Source Datasets
Я
R
Performance with Multiple Source
Datasets
Latin & Cyrillic
Performance with Multiple Source
Datasets
Latin & Cyrillic
Performance with Multiple Source
Datasets
Latin & Cyrillic
Performance with Multiple Source
Datasets
Let me tell you a story.
This study explores the concept of teaching machines using metaphors, focusing on learning by induction, transfer learning approaches, common inductive bias, instances, and features. The research offers a new approach to transfer learning through metaphors, aiming to enhance the understanding and application of machine learning techniques.
Uploaded on Oct 09, 2024 | 0 Views
Download Presentation
Please find below an Image/Link to download the presentation.
The content on the website is provided AS IS for your information and personal use only. It may not be sold, licensed, or shared on other websites without obtaining consent from the author. Download presentation by click this link. If you encounter any issues during the download, it is possible that the publisher has removed the file from their server.
E N D
Presentation Transcript
Teaching Machines to Learn by Metaphors Omer Levy & Shaul Markovitch Technion Israel Institute of Technology
Transfer Learning Target (New) Source (Original)
Transfer Learning Approaches Common Inductive Bias Common Instances Common Features
Example -3 -2 0 2 3
Example -3 -2 0 2 3 0 4 9
Example -3 -2 0 2 3 ??= ??2 0 4 9
Common Inductive Bias -3 -2 0 2 3 0 4 9
Common Inductive Bias -3 -2 0 2 3 0 4 9
Common Instances -3 -2 0 2 3 0 4 9
Common Features 3 2 4 9 -2 -3 ??= ??2
Metaphors Target (New) Source (Original)
Source Concept Learner Target Metaphor Learner ?? ?? ? ? +/-
? is a perfect metaphor if: 1. ? is label preserving ???? = ??? ?? 2. ? is distribution preserving ??~?? ? ??~??
Theorem If ? is a perfect metaphor - and - ? is a source hypothesis with ?? error - then - ??? = ?? ?? is a target hypothesis with ?? error
The Metaphor Theorem If ? is an ?-perfect metaphor - and - ? is a source hypothesis with ?? error - then - ??? = ?? ?? is a target hypothesis with ? + ?? error
Redefine Transfer Learning Given source and target datasets, find a target hypothesis ? such that ?? is as small as possible.
Redefine Transfer Learning Given source and target datasets, find an ?-perfect metaphor ? such that ? is as small as possible.
Concept Learning Framework Search Algorithm Hypothesis Space Data Evaluation Function
Metaphor Learning Framework Source Search Algorithm Metaphor Space Target Evaluation Function ?
Metaphor Evaluation 1. ? is label preserving ???? = ??? ?? 2. ? is distribution preserving ??~?? ? ??~??
Metaphor Evaluation 1. ? is label preserving Empirical error over target dataset 2. ? is distribution preserving Statistical distance between ? ?? and ??
Metaphor Evaluation ?? ? ??,??
Metaphor Evaluation ?? ? ??+,??+
Metaphor Evaluation ?? ? ?? ,??
Metaphor Evaluation ?? ? ??+,??++ ?? ? ?? ,??
Metaphor Spaces General Few Degrees of Freedom Representation-Specific Bias
Dictionary-Based Metaphors cheese queso
Linear Transformations ? ? = ? ?+ ?
Which metaphor space should I use? Automatic Selection of Metaphor Spaces
Which metaphor space should I use? Automatic Selection of Metaphor Spaces Occam s Razor
Which metaphor space should I use? Automatic Selection of Metaphor Spaces Occam s Razor Structural Risk Minimization
Automatic Selection of Metaphor Spaces ?1 1 ?2 2 ?3 3 ?4 4
Automatic Selection of Metaphor Spaces ?1 1 60% ?2 90% 2 ?3 91% 3 ?4 70% 4
Reference Methods Baseline Target Only Identity Metaphor Merge State-of-the-Art Frustratingly Easy Domain Adaptation Daum , 2007 MultiTask Learning Caruana, 1997; Silver et al, 2010 TrAdaBoost Dai et al, 2007
