Dorrell, william;
Hsu, Kyle;
Hollingsworth, Luke;
Lee, Jin Hwa;
Wu, Jiajun;
Finn, Chelsea;
Latham, Peter;
... Whittington, James CR; + view all
(2025)
Range, not Independence, Drives Modularity in Biologically Inspired Representations.
In:
Proceedings 13th International Conference on Learning Representations ICLR 2025.
ICLR: Singapore, Singapore.
Preview |
Text
4777_Range_not_Independence_Dr.pdf - Published Version Download (13MB) | Preview |
Abstract
Why do biological and artificial neurons sometimes modularise, each encoding a single meaningful variable, and sometimes entangle their representation of many variables? In this work, we develop a theory of when biologically inspired networks---those that are nonnegative and energy efficient---modularise their representation of source variables (sources). We derive necessary and sufficient conditions on a sample of sources that determine whether the neurons in an optimal biologically-inspired linear autoencoder modularise. Our theory applies to any dataset, extending far beyond the case of statistical independence studied in previous work. Rather we show that sources modularise if their support is ``sufficiently spread''. From this theory, we extract and validate predictions in a variety of empirical studies on how data distribution affects modularisation in nonlinear feedforward and recurrent neural networks trained on supervised and unsupervised tasks. Furthermore, we apply these ideas to neuroscience data, showing that range independence can be used to understand the mixing or modularising of spatial and reward information in entorhinal recordings in seemingly conflicting experiments. Further, we use these results to suggest alternate origins of mixed-selectivity, beyond the predominant theory of flexible nonlinear classification. In sum, our theory prescribes precise conditions on when neural activities modularise, providing tools for inducing and elucidating modular representations in brains and machines.
| Type: | Proceedings paper |
|---|---|
| Title: | Range, not Independence, Drives Modularity in Biologically Inspired Representations |
| Event: | The Thirteenth International Conference on Learning Representations |
| Open access status: | An open access version is available from UCL Discovery |
| Publisher version: | https://openreview.net/forum?id=BxQkDog4ti |
| Language: | English |
| Additional information: | © The Author(s), 2025. This is an Open Access article distributed under the terms of the Creative Commons Attribution Licence (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. https://creativecommons.org/licenses/by/4.0/ |
| Keywords: | neuroscience, representation learning, disentanglement, modularisation, neural networks, hippocampus, cortex |
| 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/10207676 |
Archive Staff Only
 |
View Item |
