Gradient-adjusted Incremental Target Propagation Provides Effective Credit Assignment in Deep Neural Networks

TL;DR

This paper introduces an improved biologically plausible learning algorithm, GAIT-prop, that effectively trains deep neural networks on complex datasets like ImageNet, addressing previous scalability limitations.

Contribution

The paper demonstrates that GAIT-prop can scale to deep networks and large datasets, providing a biologically plausible alternative to backpropagation.

Findings

GAIT-prop successfully trains deep networks on ImageNet.

It overcomes previous limitations in scaling biological plausibility methods.

The method achieves competitive performance on complex tasks.

Abstract

Many of the recent advances in the field of artificial intelligence have been fueled by the highly successful backpropagation of error (BP) algorithm, which efficiently solves the credit assignment problem in artificial neural networks. However, it is unlikely that BP is implemented in its usual form within biological neural networks, because of its reliance on non-local information in propagating error gradients. Since biological neural networks are capable of highly efficient learning and responses from BP trained models can be related to neural responses, it seems reasonable that a biologically viable approximation of BP underlies synaptic plasticity in the brain. Gradient-adjusted incremental target propagation (GAIT-prop or GP for short) has recently been derived directly from BP and has been shown to successfully train networks in a more biologically plausible manner. However, so far, GP has only been shown to work on relatively low-dimensional problems, such as handwritten-digit recognition. This work addresses some of the scaling issues in GP and shows it to perform effective multi-layer credit assignment in deeper networks and on the much more challenging ImageNet dataset.