Weakly Connected Neural Networks

Frank C Hoppensteadt

ISBN 10: 0387949488 / ISBN 13: 9780387949482

Edité par Springer New York Jul 1997, 1997

A propos de cet article

Neuware - This book is devoted to an analysis of general weakly connected neural networks (WCNNs) that can be written in the form (0.1) m Here, each Xi E IR is a vector that summarizes all physiological attributes of the ith neuron, n is the number of neurons, Ii describes the dynam ics of the ith neuron, and gi describes the interactions between neurons. The small parameter EUR indicates the strength of connections between the neurons. Weakly connected systems have attracted much attention since the sec ond half of seventeenth century, when Christian Huygens noticed that a pair of pendulum clocks synchronize when they are attached to a light weight beam instead of a wall. The pair of clocks is among the first weakly connected systems to have been studied. Systems of the form (0.1) arise in formal perturbation theories developed by Poincare, Liapunov and Malkin, and in averaging theories developed by Bogoliubov and Mitropolsky.

N° de réf. du vendeur 9780387949482

Détails bibliographiques

• Titre: Weakly Connected Neural Networks
• Éditeur: Springer New York Jul 1997
• Date de parution: 1997
• Langue: anglais
• ISBN à 10 chiffres: 0387949488
• ISBN à 13 chiffres: 9780387949482
• Reliure: Buch
• État de l'article: Neu
• Dimensions: 241 L x 161 H x 25 P (en millimètres) 241 millimètres de largeur par 161 millimètres de hauteur par 25 millimètres de profondeur
• Poids: 726 grammes

A propos de ce titre

Synopsis

Devoted to local and global analysis of weakly connected systems with applications to neurosciences, this book uses bifurcation theory and canonical models as the major tools of analysis. It presents a systematic and well motivated development of both weakly connected system theory and mathematical neuroscience, addressing bifurcations in neuron and brain dynamics, synaptic organisations of the brain, and the nature of neural codes. The authors present classical results together with the most recent developments in the field, making this a useful reference for researchers and graduate students in various branches of mathematical neuroscience.