A New Approach to Adaptive Filters
The early works around 1960 on learning machines may be characterized as attempts to implement artificial intelligence using formal models of neurons and Perceptron networks, obviously in the hope that more and more complex functions would gradually evolve from such structures. There is no doubt about the biological organisms having that fundamental organization. Why was the success in artificial constructs not straightforward as expected? Below I am aiming at a critical analysis, mainly with an objective to find amendments to the early ideas.
KeywordsInput Vector Asymptotic Solution Input Pattern Control Effect Projection Matrix
Unable to display preview. Download preview PDF.
- 4.5A. Lansner: Information Processing in a Network of Model Neurons: A Computer Simulation Study, in TRITA-NA-8211, The Royal Inst of Technology, Stockholm (1982)Google Scholar
- 4.7Papers delivered by W. Rail and G. Shepherd at the Symp. “Computer Simulation in Brain Science”, Copenhagen (20–22 August, 1986); Proc. to be edited by R. Cotterill will be published by Cambridge Uni. PressGoogle Scholar
- 4.9W.E. Reichardt, T. Poggio (eds.): Theoretical Approaches in Neurobiology (MIT Press, Cambridge, MA 1981)Google Scholar
- 4.12T. Kohonen, E. Oja, M. Ruohonen: Adaptation of a linear system to a finite set of patterns occurring in an arbitrarily varying order. Acta Poly- tech. Scand. Math. Computer Sci. Ser. 25 (1974)Google Scholar
- 4.13E. Oja: IEEE TC-27, 65 (1979)Google Scholar
- 4.14T. Kohonen: A class of randomly organized associative memories, Acta Poly tech. Scand. Electr. Eng. Ser. 25 (1971)Google Scholar
- 4.15T. Kohonen: IEEE Trans. C-21, 353 (1972)Google Scholar
- 4.17W.T. Reid: Riccati Differential Equations (Academic, New York 1969)Google Scholar
- 4.18J.K. Hale: Ordinary Differential Equations (Wiley, New York 1969)Google Scholar
- 4.19D.K. Faddeev, V.N. Faddeeva: Computational Methods of Linear Algebra (Freeman, San Francisco 1963)Google Scholar