English

A biologically plausible neural network for local supervision in cortical microcircuits

Neural and Evolutionary Computing 2020-12-01 v1 Machine Learning Neurons and Cognition

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.

Keywords

Cite

@article{arxiv.2011.15031,
  title  = {A biologically plausible neural network for local supervision in cortical microcircuits},
  author = {Siavash Golkar and David Lipshutz and Yanis Bahroun and Anirvan M. Sengupta and Dmitri B. Chklovskii},
  journal= {arXiv preprint arXiv:2011.15031},
  year   = {2020}
}

Comments

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

R2 v1 2026-06-23T20:36:37.559Z