Adaptive models in neural networks
Artificial neural networks (ANNs) are principally attractive for their high degree of parallelism, for their associative memory properties, and for their ability to swiftly compute “near-optimal” solutions to highly constrained optimization problems. In this paper we examine the essential adaptive models that have been proposed for ANNs.
Unable to display preview. Download preview PDF.
- Hebb,D.O, (1949), The Organization of Behavior, New York: WileyGoogle Scholar
- Klopf,A.H., (1982), The Hedonistic Neuron: A Theory of Memory, Learning and Intelligence, New York: Hemisphere Publ. Corp.Google Scholar
- Ligomenides,P. A., (1993), “Cooperative Computers With Extended Computational Capabilities”, Proceedings of European Symp. on ANNs, ESANN'93, Brussels, Belgium, April 7–9Google Scholar
- Ligomenides,P.A., (1992), “Computation and Learning Paradigms for Biologically Inspired Intelligent Computing”, Proc. 2nd Int'l Conf. on Fuzzy Logic and Neural Networks, Iizuka'92, Iizuka, Japan, July 17–22, 1992Google Scholar
- Ligomenides,P.A., (1991), “Cooperative Computing and Neural Networks”, in Lecture Notes in Computer Science: Artificial Neural Networks, A.Prieto (Ed), vol. 540, Springer-VerlagGoogle Scholar
- Ligomenides,P.A., (1991), “Computation and Uncertainty in Regulated Synergetic Machines”, in Lecture Notes in Computer Science: Uncertainty in Knowledge Bases, B.Bouchon-Meunier, R.R.Yager, LA.Zadeh, (Eds), vol. 521, Springer-VerlagGoogle Scholar
- Rumelhart,D., et al, (1986), “A general Framework for Parallel Distributed Processing”, Ch.2, in Parallel Distributed Processing, Explorations in the Microstructure of Cognition, vol.1, Cambridge, Mass, The MIT PressGoogle Scholar
- Sutton,R. and A.,Barto, (1981), “Toward a Modern Theory of Adaptive Networks: Expectation and Prediction”, Psychological Review 88, no2:135–170Google Scholar