Contrastive Hebbian Feedforward Learning for Neural Networks

• Published in: IEEE transaction on neural networks and learning systems Vol. 31; no. 6; pp. 2118 - 2128
• Main Author: Kermiche, Noureddine
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.06.2020; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Back propagation; Binary stochastic neurons; contrastive divergence; contrastive Hebbian; Correlation; deep learning; Feedback circuits; Feedforward neural networks; Feedforward systems; Learning; Learning algorithms; Learning systems; Machine learning; Neural networks; Neurons; Stochasticity; Training
• ISSN: 2162-237X; 2162-2388; 2162-2388
• DOI: 10.1109/TNNLS.2019.2927957

This paper addresses the biological plausibility of both backpropagation (BP) and contrastive Hebbian learning (CHL) used in the Boltzmann machines. The main claim of this paper is that CHL is a general learning algorithm that can be used to steer feedforward networks toward desirable outcomes, and steer them away from undesirable outcomes without any need for the specialized feedback circuit of BP or the symmetric connections used by the Boltzmann machines. After adding perturbations during the learning phase to all the neurons in the network, multiple feedforward outcomes are classified into Hebbian and anti-Hebbian sets based on the network predictions. The algorithm is applied to networks when optimizing a loss objective where BP excels and is also applied to networks with stochastic binary outputs where BP cannot be easily applied. The power of the proposed algorithm lies in its simplicity where both learning and gradient estimation through stochastic binary activations are combined into a single local Hebbian rule. We will also show that both Hebbian and anti-Hebbian correlations are evaluated from the readily available signals that are fundamentally different from CHL used in the Boltzmann machines. We will demonstrate that the new learning paradigm where Hebbian/anti-Hebbian correlations are based on correct/incorrect predictions is a powerful concept that separates this paper from other biologically inspired learning algorithms.