A Heterosynaptic Learning Rule for Neural Networks

TL;DR

This paper introduces a neurobiologically inspired stochastic heterosynaptic learning rule that combines Hebbian and reinforcement learning, demonstrating effective training of neural networks including XOR, with polynomial scaling of learning time.

Contribution

The paper presents a novel heterosynaptic learning rule that incorporates remote synaptic effects and combines unsupervised and supervised learning, advancing neurobiological plausibility and network training efficiency.

Findings

Effective learning of parity functions including XOR

Works well even with noise in the data

Learning time scales polynomially with number of patterns

Abstract

In this article we intoduce a novel stochastic Hebb-like learning rule for neural networks that is neurobiologically motivated. This learning rule combines features of unsupervised (Hebbian) and supervised (reinforcement) learning and is stochastic with respect to the selection of the time points when a synapse is modified. Moreover, the learning rule does not only affect the synapse between pre- and postsynaptic neuron, which is called homosynaptic plasticity, but effects also further remote synapses of the pre- and postsynaptic neuron. This more complex form of synaptic plasticity has recently come under investigations in neurobiology and is called heterosynaptic plasticity. We demonstrate that this learning rule is useful in training neural networks by learning parity functions including the exclusive-or (XOR) mapping in a multilayer feed-forward network. We find, that our stochastic learning rule works well, even in the presence of noise. Importantly, the mean learning time increases with the number of patterns to be learned polynomially, indicating efficient learning.