GAIT-prop: A biologically plausible learning rule derived from backpropagation of error
This addresses the problem of developing biologically plausible learning rules for neural circuits, though it is incremental as it builds on existing target propagation methods.
The paper tackled the biological implausibility of backpropagation in neural networks by deriving GAIT-prop, a modified target propagation method that achieves exact equivalence to backpropagation under orthogonal weight conditions, and demonstrated near-identical performance in computer vision experiments.
Traditional backpropagation of error, though a highly successful algorithm for learning in artificial neural network models, includes features which are biologically implausible for learning in real neural circuits. An alternative called target propagation proposes to solve this implausibility by using a top-down model of neural activity to convert an error at the output of a neural network into layer-wise and plausible 'targets' for every unit. These targets can then be used to produce weight updates for network training. However, thus far, target propagation has been heuristically proposed without demonstrable equivalence to backpropagation. Here, we derive an exact correspondence between backpropagation and a modified form of target propagation (GAIT-prop) where the target is a small perturbation of the forward pass. Specifically, backpropagation and GAIT-prop give identical updates when synaptic weight matrices are orthogonal. In a series of simple computer vision experiments, we show near-identical performance between backpropagation and GAIT-prop with a soft orthogonality-inducing regularizer.