A biologically plausible neural network for local supervision in cortical microcircuits

Abstract

The backpropagation algorithm is an invaluable tool for training artificial neural networks; however, because of a weight sharing requirement, it does not provide a plausible model of brain function. Here, in the context of a two-layer network, we derive an algorithm for training a neural network which avoids this problem by not requiring explicit error computation and backpropagation. Furthermore, our algorithm maps onto a neural network that bears a remarkable resemblance to the connectivity structure and learning rules of the cortex. We find that our algorithm empirically performs comparably to backprop on a number of datasets.

Abstract presented at the NeurIPS 2020 workshop "Beyond Backpropagation". arXiv admin note: text overlap with arXiv:2010.12660