PhD Thesis: "Learning to See Analogies: A Connectionist Exploration"

[Douglas Blank]

The following Ph.D. thesis is now available via 

  - anonymous ftp (ftp://dangermouse.uark.edu/pub/thesis)
  - web site (http://www.uark.edu/~dblank/thesis.html)
  - hardcopy (send address to dblank at comp.uark.edu)

It is about 200 pages long and the chapters can be retrieved 
individually as PostScript or PDF files. (Specific retrieval 
instructions below).

Title: Learning to See Analogies: A Connectionist Exploration

Douglas S. Blank
Joint Ph.D. in Cognitive Science and Computer Science
Indiana University, Bloomington

ABSTRACT

This dissertation explores the integration of learning and
analogy-making through the development of a computer program, called
Analogator, that learns to make analogies by example. By "seeing" many
different analogy problems, along with possible solutions, Analogator
gradually develops an ability to make new analogies. That is, it
learns to make analogies by analogy. This approach stands in contrast
to most existing research on analogy-making, in which typically the a
priori existence of analogical mechanisms within a model is assumed.

The present research extends standard connectionist methodologies by
developing a specialized associative training procedure for a
recurrent network architecture. The network is trained to divide input
scenes (or situations) into appropriate figure and ground
components. Seeing one scene in terms of a particular figure and
ground provides the context for seeing another in an analogous
fashion. After training, the model is able to make new analogies
between novel situations.

Analogator has much in common with lower-level perceptual models of
categorization and recognition; it thus serves as a unifying framework
encompassing both high-level analogical learning and low-level
perception. This approach is compared and contrasted with other
computational models of analogy-making. The model's training and
generalization performance is examined, and limitations are
discussed. 

===========================================================

Title, Abstract, Acknowledgments, Contents
  0_intro.pdf 54k
  0_intro.ps.gz 71k

Chapter 1 INTRODUCTION
  1_ch.pdf 172k
  1_ch.ps.gz 187k

Chapter 2 ANALOGY-MAKING, LEARNING, AND GENERALIZATION 
  2_ch.pdf 32k
  2_ch.ps.gz 40k

Chapter 3 CONNECTIONIST FOUNDATIONS 
  3_ch.pdf 221k
  3_ch.ps.gz 189k

Chapter 4 THE ANALOGATOR MODEL
  4_ch.pdf 578k
  4_ch.ps.gz 390k

Chapter 5 EXPERIMENTAL RESULTS
  5_ch.pdf 702k
  5_ch.ps.gz 566k

Chapter 6 COMPARISONS WITH OTHER MODELS OF ANALOGY-MAKING
  6_ch.pdf 305k
  6_ch.ps.gz 276k

Chapter 7 CONCLUSION 
  7_ch.pdf 16k
  7_ch.ps.gz 24k

APPENDICES, REFERENCES 
  8_end.pdf 57k
  8_end.ps.gz 91k

Everything
  all.pdf 2M
  all.ps.gz 1M

===========================================================

FTP instructions:

(e.g., to retrieve Chapter 1)

unix> ftp dangermouse.uark.edu
Name: anonymous
Password: youremail at domain
ftp> cd pub/thesis
ftp> get 1_ch.ps.gz
ftp> bye
unix> gunzip 1_ch.ps.gz
unix> lpr 1_ch.ps

=====================================================================
dblank at comp.uark.edu            Douglas Blank, University of Arkansas
Assistant Professor                                  Computer Science
==================== http://www.uark.edu/~dblank ====================