The ''brain-state-in-a-box'' neural model is a gradient descent algorithm (Q1072966)

The brain-state-in-a-box (BSB) neural model [\textit{J. A. Anderson}, J. W. Silverstein, \textit{S. A. Ritz} and \textit{R. S. Jones}, Distinctive features, categorical perception, and probability learning: Some applications of a neural model. Psychological Review, 84, 413-451 (1977)] is a pattern categorization device inspired by neurophysiological considerations. This model has additionally been applied to a fairly diverse range of psychological phenomena. In this paper, the BSB model is demonstrated to be a deterministic constrained gradient descent algorithm that minimizes a quadratic cost function. A formal proof that all trajectories of the BSB algorithm in state vector space approach the set of system equilibrium points, under certain specific conditions, is presented. Some conditions regarding the existence of global energy minima are also briefly discussed.