The Hystery Unit - A Short Term Memory Model for Computational Neurons
Mai-Jan Tom, Manoel Fernando Tenorio · Purdue e-Pubs (Purdue University System) · 1990
In this paper, a model of short term memory is introduced. This model is inspired by the transient behavior of neurons and magnetic storage as memory. The transient response of a neuron is hypothesized to be a combination of a pair of sigmoids, and a relation is drawn to the hysteresis loop characteristics of magnetic materials. A model is created as a composition of two coupled families of curves. Two theorems are derived regarding the asymptotic convergence behavior of the model. Another conjecture claims that the model retains full memory of all past unit step inputs. 2 Introduction The sigmoid like graded response curve of a neuron used in neural computation research is often taken to be a scaled, displaced hyperbolic tangent. The graded response of the neuron (i.e. frequency of firing verses stimulus strength) to a stimulus is measured by probing neurons in a subject exposed to certain stimuli in a controlled environment. However this response includes measurement error and the...