Pehlevan, Cengiz;
Erdogan, Alper T;
Bozkurt, Bariscan;
(2023)
Correlative Information Maximization: A Biologically
Plausible Approach to Supervised Deep Neural
Networks without Weight Symmetry.
In:
Proceedings of the 37th Conference on Neural Information Processing Systems (NeurIPS 2023).
(pp. pp. 1-37).
NeurIPS
(In press).
Preview |
Text
CorInfoMax_Supervised-2.pdf - Accepted Version Download (6MB) | Preview |
Abstract
The backpropagation algorithm has experienced remarkable success in training large-scale artificial neural networks; however, its biological plausibility has been strongly criticized, and it remains an open question whether the brain employs supervised learning mechanisms akin to it. Here, we propose correlative information maximization between layer activations as an alternative normative approach to describe the signal propagation in biological neural networks in both forward and backward directions. This new framework addresses many concerns about the biological-plausibility of conventional artificial neural networks and the backpropagation algorithm. The coordinate descent-based optimization of the corresponding objective, combined with the mean square error loss function for fitting labeled supervision data, gives rise to a neural network structure that emulates a more biologically realistic network of multi-compartment pyramidal neurons with dendritic processing and lateral inhibitory neurons. Furthermore, our approach provides a natural resolution to the weight symmetry problem between forward and backward signal propagation paths, a significant critique against the plausibility of the conventional backpropagation algorithm. This is achieved by leveraging two alternative, yet equivalent forms of the correlative mutual information objective. These alternatives intrinsically lead to forward and backward prediction networks without weight symmetry issues, providing a compelling solution to this long-standing challenge.
| Type: | Proceedings paper |
|---|---|
| Title: | Correlative Information Maximization: A Biologically Plausible Approach to Supervised Deep Neural Networks without Weight Symmetry |
| Event: | 37th Conference on Neural Information Processing Systems (NeurIPS 2023) |
| Open access status: | An open access version is available from UCL Discovery |
| Publisher version: | https://openreview.net/forum?id=TUGoUNkccV |
| 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. |
| Keywords: | Correlative information maximization, Biologically-plausible learning, Multi-compartment neural model |
| 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/10181230 |
Archive Staff Only
 |
View Item |
