Removing Epistemological Bias From Empirical Observation of Neural Networks

Abstract

This paper addresses the application of neural network research to a theory of autonomous systems. Neural networks, while enjoying considerable success in autonomous systems applications, have failed to provide a firm theoretical underpinning to neural systems embedded in their natural ecological context. This paper proposes a stochastic formulation of such an embedding. A neural system derived from the cell membrane equation is shown to exhibit a stochastic dynamic which tracks an environmental process. The activity of a node is interpreted in the context of this external stochastic process, in the light of its interdependence, which is now of statistical formulation, on the nodes to which it projects.