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

Modelling continual learning in humans with Hebbian context gating and exponentially decaying task signals

Flesch, T; Nagy, DG; Saxe, A; Summerfield, C; (2023) Modelling continual learning in humans with Hebbian context gating and exponentially decaying task signals. PLoS Computational Biology , 19 (1) , Article e1010808. 10.1371/journal.pcbi.1010808. Green open access

[thumbnail of Modelling continual learning in humans with Hebbian context gating and exponentially decaying task signals.pdf]
Preview
Text
Modelling continual learning in humans with Hebbian context gating and exponentially decaying task signals.pdf - Published Version

Download (2MB) | Preview

Abstract

Humans can learn several tasks in succession with minimal mutual interference but perform more poorly when trained on multiple tasks at once. The opposite is true for standard deep neural networks. Here, we propose novel computational constraints for artificial neural networks, inspired by earlier work on gating in the primate prefrontal cortex, that capture the cost of interleaved training and allow the network to learn two tasks in sequence without forgetting. We augment standard stochastic gradient descent with two algorithmic motifs, socalled "sluggish"task units and a Hebbian training step that strengthens connections between task units and hidden units that encode task-relevant information. We found that the "sluggish"units introduce a switch-cost during training, which biases representations under interleaved training towards a joint representation that ignores the contextual cue, while the Hebbian step promotes the formation of a gating scheme from task units to the hidden layer that produces orthogonal representations which are perfectly guarded against interference. Validating the model on previously published human behavioural data revealed that it matches performance of participants who had been trained on blocked or interleaved curricula, and that these performance differences were driven by misestimation of the true category boundary.

Type: Article
Title: Modelling continual learning in humans with Hebbian context gating and exponentially decaying task signals
Location: United States
Open access status: An open access version is available from UCL Discovery
DOI: 10.1371/journal.pcbi.1010808
Publisher version: https://doi.org/10.1371/journal.pcbi.1010808
Language: English
Additional information: © 2023 Flesch et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
Keywords: Animals, Humans, Learning, Neural Networks, Computer, Machine Learning, Prefrontal Cortex, Curriculum
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/10166620
Downloads since deposit
17Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item