UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

Towards Biologically Plausible Convolutional Networks

Pogodin, R; Mehta, Y; Lillicrap, TP; Latham, PE; (2021) Towards Biologically Plausible Convolutional Networks. In: Advances in Neural Information Processing Systems 34 pre-proceedings (NeurIPS 2021). NeurIPs (In press). Green open access

[thumbnail of Latham_towards_biologically_plausible.pdf]
Preview
Text
Latham_towards_biologically_plausible.pdf - Accepted Version

Download (2MB) | Preview

Abstract

Convolutional networks are ubiquitous in deep learning. They are particularly useful for images, as they reduce the number of parameters, reduce training time, and increase accuracy. However, as a model of the brain they are seriously problematic, since they require weight sharing - something real neurons simply cannot do. Consequently, while neurons in the brain can be locally connected (one of the features of convolutional networks), they cannot be convolutional. Locally connected but non-convolutional networks, however, significantly underperform convolutional ones. This is troublesome for studies that use convolutional networks to explain activity in the visual system. Here we study plausible alternatives to weight sharing that aim at the same regularization principle, which is to make each neuron within a pool react similarly to identical inputs. The most natural way to do that is by showing the network multiple translations of the same image, akin to saccades in animal vision. However, this approach requires many translations, and doesn't remove the performance gap. We propose instead to add lateral connectivity to a locally connected network, and allow learning via Hebbian plasticity. This requires the network to pause occasionally for a sleep-like phase of "weight sharing". This method enables locally connected networks to achieve nearly convolutional performance on ImageNet and improves their fit to the ventral stream data, thus supporting convolutional networks as a model of the visual stream.

Type: Proceedings paper
Title: Towards Biologically Plausible Convolutional Networks
Open access status: An open access version is available from UCL Discovery
Publisher version: https://proceedings.neurips.cc/paper/2021/hash/746...
Language: English
Additional information: This version is the author accepted manuscript. For information on re-use, please refer to the publisher's terms and conditions.
UCL classification: UCL
UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences
UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences > Faculty of Life Sciences
UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences > Faculty of Life Sciences > Gatsby Computational Neurosci Unit
URI: https://discovery.ucl.ac.uk/id/eprint/10141846
Downloads since deposit
74Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item