This book is the third in a series based on conferences sponsored by the Metroplex Institute for Neural Dynamics, an interdisciplinary organization of neural network professionals in academia and industry. The topics selected are of broad interest to both those interested in designing machines to perform intelligent functions and those interested in studying how these functions are actually performed by living organisms and generate discussion of basic and controversial issues in the study of mind.
The topic of optimality was chosen because it has provoked considerable discussion and controversy in many different academic fields. There are several aspects to the issue of optimality. First, is it true that actual behavior and cognitive functions of living animals, including humans, can be considered as optimal in some sense? Second, what is the utility function for biological organisms, if any, and can it be described mathematically? Rather than organize the chapters on a "biological versus artificial" basis or by what stance they took on optimality, it seemed more natural to organize them either by what level of questions they posed or by what intelligent functions they dealt with.
The book begins with some general frameworks for discussing optimality, or the lack of it, in biological or artificial systems. The next set of chapters deals with some general mathematical and computational theories that help to clarify what the notion of optimality might entail in specific classes of networks. The final section deals with optimality in the context of many different high-level issues, including exploring one's environment, understanding mental illness, linguistic communication, and social organization. The diversity of topics covered in this book is designed to stimulate interdisciplinary thinking and speculation about deep problems in intelligent system organization.
Contents: Preface. Part I: What Is the Role of Optimality? D.S. Levine, Don't Just Stand There, Optimize Something! P.J. Werbos, Optimization: A Foundation for Understanding Consciousness. S. Leven, Negotiating Inside the Brain -- and Out: The Microfoundations Project. D.G. Stork, B. Jackson, S. Walker, Nonoptimality in a Neurobiological System. W.R. Elsberry, Optimality and Strategies in Biological and Artificial Neural Networks. M.R. DeYong, T. Eskridge, Properties of Optimality in Neural Networks. Part II: Quantitative Foundations of Neural Optimality. P.S. Prueitt, Optimality and Options in the Context of Behavioral Choice. I. Parberry, Knowledge, Understanding, and Computational Complexity. R.M. Golden, Optimal Statistical Goals for Neural Networks Are Necessary, Important, and Practical. G.D. Tattersall, Rule Induction and Mapping Completion in Neural Networks. R.E. Dorsey, J.D. Johnson, Evolution of Dynamic Reconfigurable Neural Networks: Energy Surface Optimality Using Genetic Algorithms. A. Jagota, Optimization by a Hopfield-Style Network. Part III: Optimality in Learning, Cognition, and Perception. D.C. Chance, J.Y. Cheung, S. Lykins, A.W. Lawton, An Examination of Mathematical Models of Learning in a Single Neuron. S. Bengio, Y. Bengio, J. Cloutier, J. Gescei, On the Optimization of a Synaptic Learning Rule. G.A. Carpenter, Spatial Pattern Learning, Catastrophic Forgetting, and Optimal Rules of Synaptic Transmission. H. Abdi, D. Valentin, A.J. O'Toole, A Generalized Autoassociator Model for Face Processing and Sex Categorization: From Principal Components to Multivariate Analysis. J. Bhaumik, B. Bhaumik, A Neural Network for Determining Subjective Contours. Part IV: Optimality in Decision, Communication, and Control. H. Ög(the g has an upsidedown circumflex -- a "v" to be found at the WordPerfect stage)men, R.V. Prakash, A Developmental Perspective to Neural Models of Intelligence and Learning. G-Z. Rosenstein, The Income-Choice Approach and Some Unsolved Problems of Psychopathology - A "Bridge Over Time." S. Candelaria de Ram, Communication Cognition: Interactive Nets We Weave, When We Practice to Perceive. R.T. Bradley, K.H. Pribram, Communication and Optimality in Biosocial Collectives.