Perceptrons, Reissue of the 1988 Expanded Edition with a new foreword by Léon Bottou: An Introduction to Computational Geometry

by Marvin Minsky, Seymour A. Papert, Leon Bottou

Overview

The first systematic study of parallelism in computation by two pioneers in the field.

Reissue of the 1988 Expanded Edition with a new foreword by Léon Bottou

In 1969, ten years after the discovery of the perceptron—which showed that a machine could be taught to perform certain tasks using examples—Marvin Minsky and Seymour Papert published Perceptrons, their analysis of the computational capabilities of perceptrons for specific tasks. As Léon Bottou writes in his foreword to this edition, “Their rigorous work and brilliant technique does not make the perceptron look very good. ” Perhaps as a result, research turned away from the perceptron. Then the pendulum swung back, and machine learning became the fastest-growing field in computer science. Minsky and Papert's insistence on its theoretical foundations is newly relevant.

Perceptrons —the first systematic study of parallelism in computation—marked a historic turn in artificial intelligence, returning to the idea that intelligence might emerge from the activity of networks of neuron-like entities. Minsky and Papert provided mathematical analysis that showed the limitations of a class of computing machines that could be considered as models of the brain. Minsky and Papert added a new chapter in 1987 in which they discuss the state of parallel computers, and note a central theoretical challenge: reaching a deeper understanding of how “objects” or “agents” with individuality can emerge in a network. Progress in this area would link connectionism with what the authors have called “society theories of mind. ”

Product Details

ISBN-13:	9780262534772
Publisher:	MIT Press
Publication date:	09/22/2017
Series:	The MIT Press
Edition description:	Reissue of the 1988 Expanded Edition with a new foreword by L?on Bottou
Pages:	316
Product dimensions:	6.00(w) x 8.90(h) x 0.70(d)
Age Range:	18 Years

About the Author

Marvin Minsky (1927–2016) was Toshiba Professor of Media Arts and Sciences and Donner Professor of Electrical Engineering and Computer Science at MIT. He was a cofounder of the MIT Media Lab and a consultant for the One Laptop Per Child project.

The late Seymour A. Papert was a Professor in MIT's AI Lab (1960–1980s) and MIT's Media Lab (1985–2000) and the author of Mindstorms: Children, Computers, and Powerful Ideas.

Léon Bottou is a Research Scientist at NEC Labs America.

Table of Contents

Foreword Léon Bottou vii

Prologue: A View from 1988 xv

0 Introduction 1

I Algebraic Theory of Linear Parallel Predicates 21

1 Theory of Linear Boolean Inequalities 25

2 Group Invariance of Boolean Inequalities 39

3 Parity and One-in-a-box Predicates 56

4 The "And/Or" Theorem 62

II Geometric Theory of Linear Inequalities 69

5 Ψ_connected: A Geometric Property with Unbounded Order 73

6 Geometric Patterns of Small Order: Spectra and Context 96

7 Stratification and Normalization 114

8 The Diameter-Limited Perceptron 129

9 Geometric Predicates and Serial Algorithms 136

III Learning Theory 149

10 Magnitude of the Coefficients 151

11 Learning 161

12 Linear Separation and Learning 188

13 Perceptrons and Pattern Recognition 227

Epilogue: The New Connectionism 247

Bibliographic Notes 281

Index 289