From:Tony Plate <tplate@acm.org>
To:Connectionists@cs.cmu.edu
Subject:book announcement
Date:Wed, 07 Jan 2004 00:51:45 -0700
Status:R
Message-Id: <5.1.0.14.2.20040107001451.02cbcdd8@pop6.attglobal.net>
Mime-Version: 1.0
Content-Type: text/plain; charset="us-ascii"

I'm pleased to announce the availability of my book:

"Holographic Reduced Representation: Distributed Representation
 for Cognitive Structures"
by Tony A. Plate
CSLI Lecture Notes Number 150, CSLI Publications, Stanford, CA 2003
ISBN 1575864304

Contents:
1 Introduction 1
2 Review of connectionist and distributed memory models 25
3 Holographic Reduced Representation 93
4 HRRs in the frequency domain 145
5 Using convolution-based storage in systems that learn 153
6 Estimating analogical similarity 175
7 Discussion 221

It is available on Amazon.com in paperback for US$25.
http://www.amazon.com/exec/obidos/tg/detail/-/1575864304

This book is a based on my PhD thesis.  It has been significantly
rewritten and updated for publishing as a book.  The major changes
include:
* New related work described in chapter 2
* A new section surveying techniques for learning in distributed
  representations
* Complete rewriting of the chapter on analogy processing, including:
  - redesigned experiments
  - discussion of the relationship between HRRs and kernel methods
    for computing similarity
  - clear exposition of how a HRR-based model can perform structure-
    sensitive analogy retrieval in a single-stage (cf 2-stage MAC/FAC
    model of human performance on analogy retrieval)
* Many references to new work added
* Subject and author indices added

The back cover blurb:

While neuroscientists garner success in identifying brain
regions and in analyzing individual neurons, ground is still
being broken at the intermediate scale of understanding how
neurons combine to encode information. This book proposes a
method of representing information in a computer that would
be suited for modeling the brain's methods of processing
information.

In stark contrast to traditional computing where "every
bit counts," the method proposed by Plate distributes
information over large numbers of components, which are
mathematically modeled by high-dimensional vectors.  No
single unit or even a small number of them means anything in
particular.  The meaningful entity is the total pattern over
all the units.  Superficially, the patterns appear random.

Holographic Reduced Representations (HRRs) are introduced
here to model how the brain could distribute each piece of
information among thousands of neurons.  It had been
previously thought that the semantic structure of natural
language sentences cannot be encoded practically in a
distributed representation but HRRs can overcome problems of
earlier proposals.  This work has implications for
psychology, neuroscience, linguistics, and computer science
and artificial intelligence.

More details available at http://pws.prserv.net/tap

-- Tony Plate

.