Showing papers on "Artificial neural network published in 1973"

Organization of Memory

Abstract: A new learning algorithm is presented that may have applications in the theory of natural and artificial intelligence.

The Use of Intracellular Dye Injections in the Study of Small Neural Networks

Abstract: The purpose of this paper is to review briefly some of the literature on the use of Procion dyes in Crustacea, to illustrate some of our work on the stomotogastric ganglion of the lobster, and to describe how computer technology can be used to reconstruct and quantitatively analyze dye-filled cells.

Some time-saving methods for the digital simulation of highway vehicles:

Abstract: Simulation has been used extensively as a tool for the solution of vehicle-dynamics problems. To handle nonlinear simulations of increasing size and complexity, both digital and hybrid methods have...

A computer simulation of a neuron net model as a self-organizing system.

Abstract: A neural net model is simulated on an IBM-1130 digital computer. The model includes rules for learning of the presented patterns. The learning algorithm uses an iteration procedure, in order to compute the ultimate cross coupling-coefficients between the neurons for a specific pattern. The network has a set of latent cyclic modes or reverberations. If the net is stimulated briefly, by presenting a pattern, it will subsequently either return to quiescence or settle into periodic activity in one of its cyclic modes.

Response routing in selcuk networks and lashley's dilemma

Abstract: Given a large net of modules of limited logic and memory in which connectivity is primarily to near neighbors with one-way channels, the question is asked of how responses to a generally broadcast request can be routed to the site of the request. A routing procedure which does not require site information is proposed. The procedure is based on the Selcuk Principle which maintains that in properly constructed networks routing can be achieved with each module remembering only on which input channels the request had first arrived. The procedure is successfully applied to a neural network model proposed by Eccles and to one advanced by Burns. The strongest requirement of the proposed procedure is that there be switching among output channels and this appears consistent with the findings of Chun, Raymond & Lettvin (1970) that there is selective invasion of axonal arborization. Since the Selcuk Network scheme achieves response routing on the basis of strictly local information, pursuant to the broadcast of a general message, it has applicability to content-based addressing and to computer-to-computer communication nets. It also constitutes an approach to pattern recognition whereby the image on the “retina” is transformed into a time spectrum of responses, the analysis of which yields information on angle, size, curvature, and position of the edges.

A deterministic approach to the study of neural systems.

Abstract: The deterministic mathematical model of neural networks with which we are concerning has been introduced by E. R. Caianiello. In this model the behaviour of a network is described by means of “Neuronic Equations” regarding the instantaneous activity of the net, and “Mnemonic Equations” describing the learning processes.The relevant feature of this approach is the use of matrix algebra, rather than boolean logic; this permitted to give, among other things, explicit methods for the design of networks whose reverberations cannot exceed prefixed periods no matter how coefficients are changed, as well as to investigate the role of coupling strengths in determining cyclic behaviours.The “individual” and the “global” problems of synthesis were investigated under “self-duality” conditions which characterize the so-called “normal systems”. The results obtained are employed to solve some global problem of synthesis without the use of the theory of linear inequalities.