Can I read Convergence and divergence in neural networks: Processing of chaos and biological analogy on EtoBox?

Convergence and divergence in neural networks: Processing of chaos and biological analogy by George J. Mpitsos; Robert M. Burton Jr. is a Computer Science article available to read on EtoBox.

What is Convergence and divergence in neural networks: Processing of chaos and biological analogy about?

We have used simple neural networks as models to e~amine two intepT'elated biological questions: What are the.[imctional implications tf the converging and diverging projections that prq6tsely interconnect neurons? How do the dynamical features of the input signal affect the responses of such networks? In this paper we examine subsets of these questions by using error-back propagation learning as the network response in question. The dynamics of the input signals was suggested by our previous biological findings. These signals consisted of chaotic series generated by the recursive logistic equation, ×n+~ = 3.95 (1 --X,)X,, random noise, and sinefunctions. The input signals were also sent to a variety of teacher fimctions that controlled the type of computations networks were required to do. Single and double hidden-layer networks were ttsed to ~:vamine, rea7~ectivel); divergence and a combination o.l'divergence and convergence. Networks containing single and multiple inpttt /otttput units were ttsed to determine how the networks learned when they were required to pel"form single or multiple tasks on their input signals. Back propagation was po.'~)rmed "on-line" in each training tri

Who reads Convergence and divergence in neural networks: Processing of chaos and biological analogy?

Author

George J. Mpitsos; Robert M. Burton Jr.

Publisher

Elsevier Science; Elsevier ; Elsevier Ltd.; Elsevier BV (ISSN 0893-6080)

Published

1992

Language

EN

Field

Computer Science (Physical Sciences)