The Variance of Covariance Rules for Associative Matrix Memories and Reinforcement Learning

Hebbian synapses lie at the heart of most associative matrix memories (Kohonen 1987; Hinton and Anderson 1981) and are also biologically plausible (Brown et al. 1990; Baudry and Davis 1991). Their analytical and computational tractability make these memories the best understood form of distributed information storage. A variety of Hebbian algorithms for estimating the covariance between input and output patterns has been proposed. This note points out that one class of these involves stochastic estimation of the covariance, shows that the signal-to-noise ratios of the rules are governed by the variances of their estimates, and considers some parallels in reinforcement learning.

[1]  K. Abromeit Music Received , 2023, Notes.

[2]  G. Stent A physiological mechanism for Hebb's postulate of learning. , 1973, Proceedings of the National Academy of Sciences of the United States of America.

[3]  T. Sejnowski Statistical constraints on synaptic plasticity. , 1977, Journal of theoretical biology.

[4]  T. Sejnowski,et al.  Storing covariance with nonlinearly interacting neurons , 1977, Journal of mathematical biology.

[5]  W. Singer,et al.  Changes in the circuitry of the kitten visual cortex are gated by postsynaptic activity , 1979, Nature.

[6]  Teuvo Kohonen,et al.  Content-addressable memories , 1980 .

[7]  J J Hopfield,et al.  Neural networks and physical systems with emergent collective computational abilities. , 1982, Proceedings of the National Academy of Sciences of the United States of America.

[8]  Richard S. Sutton,et al.  Temporal credit assignment in reinforcement learning , 1984 .

[9]  James A. Anderson,et al.  Neurocomputing: Foundations of Research , 1988 .

[10]  M. Tsodyks,et al.  The Enhanced Storage Capacity in Neural Networks with Low Activity Level , 1988 .

[11]  Günther Palm,et al.  On the asymptotic information storage capacity of neural networks , 1988 .

[12]  Günther Palm,et al.  Local Synaptic Rules with Maximal Information Storage Capacity , 1988 .

[13]  T. Sejnowski,et al.  Associative long-term depression in the hippocampus induced by hebbian covariance , 1989, Nature.

[14]  D. Amit,et al.  Optimised network for sparsely coded patterns , 1989 .

[15]  Geoffrey E. Hinton,et al.  Parallel Models of Associative Memory , 1989 .

[16]  E. W. Kairiss,et al.  Hebbian synapses: biophysical mechanisms and algorithms. , 1990, Annual review of neuroscience.

[17]  Peter Dayan,et al.  Optimal Plasticity from Matrix Memories: What Goes Up Must Come Down , 1990, Neural Computation.

[18]  E. Vaadia,et al.  Firing patterns of single units in the prefrontal cortex and neural network models , 1990 .

[19]  Joel L. Davis,et al.  Long-term potentiation : a debate of current issues , 1991 .

[20]  David S. Touretzky,et al.  Connectionist models : proceedings of the 1990 summer school , 1991 .

[21]  B. Forrest,et al.  Neural networks with low activity levels , 1992 .