Robot Brains: Circuits and Systems for Conscious Machines

Contents

Preface

1 Introduction

1.1 General intelligence and conscious machines

1.2 How to model cognition?

1.3 The approach of this book

2 Information, meaning and representation

2.1 Meaning and the nonnumeric brain

2.2 Representation of information by signal vectors

2.2.1 Single signal and distributed signal representations

2.2.2 Representation of graded values

2.2.3 Representation of significance

2.2.4 Continuous versus pulse train signals

3 Associative neural networks

3.1 Basic circuits

3.1.1 The associative function

3.1.2 Basic neuron models

3.1.3 The Haikonen associative neuron

3.1.4 Threshold functions

3.1.5 The linear associator

3.2 Nonlinear associators

3.2.1 The nonlinear associative neuron group

3.2.2 Simple binary associator

3.2.3 Associator with continuous weight values

3.2.4 Bipolar binary associator

3.2.5 Hamming distance binary associator

3.2.6 Enhanced Hamming distance binary associator

3.2.7 Enhanced simple binary associator

3.3 Interference in the association of signals and vectors

3.4 Recognition and classification by the associative neuron group

3.5 Learning

3.5.1 Instant Hebbian learning

3.5.2 Correlative Hebbian learning

3.6 Match, mismatch and novelty

3.7 The associative neuron group and noncomputable functions

4 Circuit assemblies

4.1 The associative neuron group

4.2 The inhibit neuron group

4.3 Voltage-to-single signal (V/SS) conversion

4.4 Single signal-to-voltage (SS/V) conversion

4.5 The ‘Winner-Takes-All’ (WTA) circuit

4.6 The ‘Accept-and-Hold’ (AH) ...