Modelling Perception With Artificial Neural Networks

by Edited by Colin R. Tosh , Graeme D. Ruxton

• ISBN13: 9780521763950
• ISBN10: 0521763959
• Edition: 1st
• Format: Hardcover
• Copyright: 2010-07-26
• Publisher: Cambridge University Press

Summary

Studies of the evolution of animal signals and sensory behaviour have more recently shifted from considering 'extrinsic' (environmental) determinants to 'intrinsic' (physiological) ones. The drive behind this change has been the increasing availability of neural network models. With contributions from experts in the field, this book provides a complete survey of artificial neural networks. The book opens with two broad, introductory level reviews on the themes of the book: neural networks as tools to explore the nature of perceptual mechanisms, and neural networks as models of perception in ecology and evolutionary biology. Later chapters expand on these themes and address important methodological issues when applying artificial neural networks to study perception. The final chapter provides perspective by introducing a neural processing system in a real animal. The book provides the foundations for implementing artificial neural networks, for those new to the field, along with identifying potential research areas for specialists.

Table of Contents

Introduction. Modelling perception with artificial neural networks

General Themes

Neural networks for perceptual processing: from simulation tools to theories

Sensory ecology and perceptual allocation: new prospects for neural networks

The Use of Artificial Neural Networks to Elucidate the Nature of Perceptual Processes in Animals

Correlation versus gradient type motion detectors: the pros and cons

Spatial constancy and the brain: insights from neural networks

The interplay of Pavlovian and instrumental processes in devaluation experiments: a computational embodied neuroscience model tested with a simulated rat

Evolution, (sequential) learning and generalization in modular and nonmodular visual neural networks

Effects of network structure on associative memory

Neural networks and neuro-oncology

Artificial Neural Networks as Models of Perceptual Processing in Ecology and Evolutionary Biology

Evolutionary diversification of mating behaviour: using artificial neural networks to study reproductive character displacement and speciation

Applying artificial neural networks to the study of prey coloration

Artificial neural networks in models of specialization, guild evolution and sympatric speciation

Probabilistic design principles for robust multimodal communication networks

Movement-based signalling and the physical world: modelling the changing perceptual task for receivers

Methodological Issues in the Use of Simple Feedforward Networks

How training and testing histories affect generalization: a test of simple neural networks

The need for stochastic replication of ecological neural networks

Methodological issues in modelling ecological learning with neural networks

Neural network evolution and artificial life research

Current velocity shapes the functional connectivity of benthiscapes to stream insect movement

A model biological neural network: the cephalopod vestibular system

Table of Contents provided by Publisher. All Rights Reserved.