PT  - JOURNAL ARTICLE
AU  - Nicolas Perez-Nieves
AU  - Vincent C. H. Leung
AU  - Pier Luigi Dragotti
AU  - Dan F. M. Goodman
TI  - Neural heterogeneity promotes robust learning
AID  - 10.1101/2020.12.18.423468
DP  - 2021 Jan 01
TA  - bioRxiv
PG  - 2020.12.18.423468
4099  - http://biorxiv.org/content/early/2021/01/12/2020.12.18.423468.short
4100  - http://biorxiv.org/content/early/2021/01/12/2020.12.18.423468.full
AB  - The brain has a hugely diverse, heterogeneous structure. By contrast, many functional neural models are homogeneous. We compared the performance of spiking neural networks trained to carry out difficult tasks, with varying degrees of heterogeneity. Introducing heterogeneity in membrane and synapse time constants substantially improved task performance, and made learning more stable and robust across multiple training methods, particularly for tasks with a rich temporal structure. In addition, the distribution of time constants in the trained networks closely matches those observed experimentally. We suggest that the heterogeneity observed in the brain may be more than just the byproduct of noisy processes, but rather may serve an active and important role in allowing animals to learn in changing environments.Summary Neural heterogeneity is metabolically efficient for learning, and optimal parameter distribution matches experimental data.Competing Interest StatementThe authors have declared no competing interest.