Search

A parallel processing algorithm for shrinking binary patterns to obtain single isolated elements, one for each pattern, is presented. This procedure may be used for counting patterns on a matrix, and a hardware implementation of the algorithm using large scale integrated technology is envisioned. The principal features of this method are the very small window employed (two-by-two elements), the parallel nature of the process, and the possibility of shrinking any pattern, regardless of the complexity of its configuration. Problems regarding merging and disconnection of patterns during the process as well as the determination of the maximum number of steps necessary to obtain a single isolated element from a pattern, are reviewed and discussed. An analogy with a neural network description, in terms of McCulloch-Pitts "neurons" is presented. [ABSTRACT FROM AUTHOR]

A description is presented of PLEXUS, a system which enables a user to construct and specify a neural network, to analyze the output data produced by the network, and to store and retrieve networks and data from a library. The system, operated entirely from a digital display unit, interacts directly with the user and permits easy and rapid transitions between the various phases of the modeling process. PLEXUS is designed to complement neurophysiological research so that the systematic development of neural models can be coordinated with experimental work. PLEXUS networks are built up from components representing individual neurons, external stimuli, and interconnecting fibers, each component being of a relatively detailed nature. Pro- vision is also made for the use of experimental data as input to a network. Convenient means for specification and modification of a network and extensive error-checking capabilities are provided. Data resulting from the simulation of a network may be analyzed by a variety of techniques ranging from examinations of the gross characteristics of the data to the determination of detailed statistical properties. [ABSTRACT FROM AUTHOR]