Muutke küpsiste eelistusi

Modelling Perception with Artificial Neural Networks [Kõva köide]

5.00/5 (2 hinnangut Goodreads-ist)
Edited by (University of Glasgow), Edited by (University of Leeds)
  • Formaat: Hardback, 408 pages, kõrgus x laius x paksus: 253x179x23 mm, kaal: 940 g, 11 Halftones, unspecified; 67 Line drawings, unspecified
  • Ilmumisaeg: 24-Jun-2010
  • Kirjastus: Cambridge University Press
  • ISBN-10: 0521763959
  • ISBN-13: 9780521763950
Teised raamatud teemal:
Modelling Perception with Artificial Neural NetworksSuurem pilt
  • Formaat: Hardback, 408 pages, kõrgus x laius x paksus: 253x179x23 mm, kaal: 940 g, 11 Halftones, unspecified; 67 Line drawings, unspecified
  • Ilmumisaeg: 24-Jun-2010
  • Kirjastus: Cambridge University Press
  • ISBN-10: 0521763959
  • ISBN-13: 9780521763950
Teised raamatud teemal:
Püsilink: https://www.kriso.ee/db/9780521763950.html
Märksõnad:
"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 studyperception. 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"--

Provided by publisher.

Studies of the evolution of animal signals and sensory behaviour have 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. It 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.

Muu info

A complete review of neural network models; a modern, powerful and successful tool for studying animal perception.
List of contributors
vii
Introduction: Modelling perception with artificial neural networks 1(4)
Part I General themes
5(56)
1 Neural networks for perceptual processing: from simulation tools to theories
7(28)
Kevin Gurney
2 Sensory ecology and perceptual allocation: new prospects for neural networks
35(26)
Steven M. Phelps
Part II The use of artificial neural networks to elucidate the nature of perceptual processes in animals
61(124)
3 Correlation versus gradient type motion detectors: the pros and cons
63(11)
Alexander Borst
4 Spatial constancy and the brain: insights from neural networks
74(19)
Robert L. White III
Lawrence H. Snyder
5 The interplay of Pavlovian and instrumental processes in devaluation experiments: a computational embodied neuroscience model tested with a simulated rat
93(21)
Francesco Mannella
Marco Mirolli
Gianluca Baldassarre
6 Evolution, (sequential) learning and generalisation in modular and nonmodular visual neural networks
114(20)
Raffaele Calabretta
7 Effects of network structure on associative memory
134(15)
Hiraku Oshima
Tokashi Odagaki
8 Neural networks and neuro-oncology: the complex interplay between brain tumour, epilepsy and cognition
149(36)
L. Douw
C. J. Stam
M. Klein
J. J. Heimans
J. C. Reijneveld
Part III Artificial neural networks as models of perceptual processing in ecology and evolutionary biology
185(108)
9 Evolutionary diversification of mating behaviour: using artificial neural networks to study reproductive character displacement and speciation
187(28)
Karin S. Pfennig
Michael J. Ryan
10 Applying artificial neural networks to the study of prey colouration
215(21)
Sami Merilaita
11 Artificial neural networks in models of specialisation, guild evolution and sympatric speciation
236(19)
Noel M. A. Holmgren
Niclas Norrstrom
Wayne M. Getz
12 Probabilistic design principles for robust multi-modal communication networks
255(14)
David C. Krakauer
Jessica Flack
Nihat Ay
13 Movement-based signalling and the physical world: modelling the changing perceptual task for receivers
269(24)
Richard A. Peters
Part IV Methodological issues in the use of simple feedforward networks
293
14 How training and testing histories affect generalisation: a test of simple neural networks
295(13)
Stefano Ghirlanda
Magnus Enquist
15 The need for stochastic replication of ecological neural networks
308(10)
Colin R. Tosh
Graeme D. Ruxton
16 Methodological issues in modelling ecological learning with neural networks
318(16)
Daniel W. Franks
Graeme D. Ruxton
17 Neural network evolution and artificial life research
334(17)
Dara Curran
Colm O'Riordan
18 Current velocity shapes the functional connectivity of benthiscapes to stream insect movement
351(23)
Julian D. Olden
19 A model biological neural network: the cephalopod vestibular system
374(16)
Roddy Williamson
Abdul Chrachri
Index 390
Colin Tosh is a postdoctoral researcher currently based in the Institute of Integrative and Comparative Biology, University of Leeds. He began his career as an experimental behavioural biologist, specialising in the host utilisation behaviour of insects. More recently he has extended his interests to theoretical biology and is currently interested in applying neural network models to study the impact of information degradation and bias between trophic levels (such as predator-prey and herbivore-plant). He is author of numerous papers in international journals of ecology and evolution and recently published a major review on insect behaviour. Graeme Ruxton is Professor of Theoretical Ecology at the University of Glasgow. He began life as a physicist, but ended up in behavioural ecology after a detour into statistics. His interests focus on the use of mathematical models as tools for understanding animal behaviour, with particular interest in cognitive aspects of predator-prey interactions. He has co-authored over 200 peer-reviewed papers, one textbook and two monographs. Ruxton and Tosh have several years of experience of fruitful collaboration, centred on the use of neural networks as representations of the sensory and decision-making processes of predators.