Strong Allee Effect Synaptic Plasticity Rule in an Unsupervised Learning Environment

DOI10.1162/NECO_A_01577MaRDI QIDQ6136195zbMATH OpenFDO

Authors Eddy Kwessi

Publication date 28 August 2023

Published in Neural Computation (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/2203.13650

Mathematics Subject Classification ID

Memory and learning in psychology (91E40) Neural networks for/in biological studies, artificial life and related topics (92B20) Population dynamics (general) (92D25)

Abstract: Synaptic plasticity or the ability of a brain to changes one or more of its functions or structures has generated and is sill generating a lot of interest from the scientific community especially neuroscientists. These interests especially went into high gear after empirical evidences were collected that challenged the established paradigm that human brain structures and functions are set from childhood and only modest changes were expected beyond. Early synaptic plasticity rules or laws to that regard include the basic Hebbian rule that proposed a mechanism for strengthening or weakening of synapses (weights) during learning and memory. This rule however did not account from the fact that weights must have bounded growth overtime. Thereafter, many other rules were proposed to complement the basic Hebbian rule and they also possess other desirable properties. In particular, a desirable property in synaptic plasticity rule is that the ambient system must account for inhibition which is often achieved if the rule used allows for a lower bound in synaptic weights. In this paper, we propose a synaptic plasticity rule inspired from the Allee effect, a phenomenon often observed in population dynamics. We show properties such such as synaptic normalization, competition between weights, de-correlation potential, and dynamic stability are satisfied. We show that in fact, an Allee effect in synaptic plasticity can be construed as an absence of plasticity.

Recommendations

• A unifying framework of synaptic and intrinsic plasticity in neural populations
• Redistribution of Synaptic Efficacy Supports Stable Pattern Learning in Neural Networks
• Optimality Model of Unsupervised Spike-Timing-Dependent Plasticity: Synaptic Memory and Weight Distribution
• Reinforcement Learning Through Modulation of Spike-Timing-Dependent Synaptic Plasticity
• scientific article; zbMATH DE number 1928622
• Synergies Between Intrinsic and Synaptic Plasticity Mechanisms
• Self-organization of a recurrent network under ongoing synaptic plasticity

Cited in

(4)

• Biologically plausible learning in neural networks with modulatory feedback
• scientific article; zbMATH DE number 1254052 (Why is no real title available?)
• Constrained plasticity reserve as a natural way to control frequency and weights in spiking neural networks
• Perspective: Allee effects in theory and reality

This page was built for publication: Strong Allee Effect Synaptic Plasticity Rule in an Unsupervised Learning Environment

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6136195)