Editors: Earl Mac Cormac and Maxim I. Stamenov.
This collective volume is the first to discuss systematically what are the possibilities to model different aspects of brain and mind functioning with the formal means of fractal geometry and deterministic chaos. At stake here is not an approximation to the way of actual performance, but the possibility of brain and mind to implement nonlinear dynamic patterns in their functioning. The contributions discuss the following topics (among others): the edge-of-chaos dynamics in recursively organized neural systems and in intersensory interaction, the fractal timing of the neural functioning on different scales of brain networking, aspects of the fractal neurodynamics and quantum chaos in novel biophysics, the fractal maximum-power evolution of brain and mind, the chaotic dynamics in the development of consciousness, etc. It is suggested that the margins of our capacity for phenomenal experience, are fractal-limit phenomena. Here the possibilities to prove the plausibility of fractal modeling with appropriate experimentation and rational reconstruction are also discussed. A conjecture is made that the brain vs. mind differentiation becomes possible, most probably, only with the imposition of appropriate symmetry groups implementing a flowing interface of features of local vs. global brain dynamics.
Advances in Consciousness Research, Volume 7.
John Benjamins Publishing Company
Amsterdam/Philadelphia. 1996
The authors, who have been team-teaching the material in a one-semester course over the past six years, describe most of the basic neural network models (with several detailed solved examples) and discuss their rationale and relative advantages. Their approach requires little mathematical or technical background. Written from a computer science and statistics point of view, the text stresses links to contiguous fields and can serve as a first course for students in economics and management.
The first chapter presents the basic concepts and tackles important yet rarely addressed questions related to the use of neural networks in practical situations. The material is structured around classes of problems to which networks can be applied. Topics include supervised learning (single layer and multilayer networks), unsupervised learning, associative models, and optimization methods.
The most frequently used algorithms are introduced early on, right after perceptrons, so that these can form the basis for initiating course projects. Algorithms published as late as 1995 are included. All of the algorithms are presented using block-structured pseudo-code, and exercises are provided throughout. The book is accompanied by software implementing many commonly used neural algorithms.
Kishan Mehrotra is Professor and Chilukuri K. Mohan is Associate Professor at the School of Computer and Information Science, Syracuse University. Sanjay Ranks is Associate Professor at the University of Florida, Gainesville.
Complex Adaptive Systems series.
A Bradford Book
The MIT Press
Cambridge, Massachusetts. 1997