Multitask training grows brain-like modularity in neural networks
Task demands, not just physical constraints, can induce modularity — a testable new path for brain-inspired architecture design.
ImportanceLocalEvidenceE3 inspectableWrite-upQuick
Multitask training drives recurrent neural networks to spontaneously develop modular structure, resembling biological brain networks more closely than single-task training does — the finding of a team's study published in Nature Machine Intelligence.
Prevailing explanations attribute the brain's modularity to physical constraints such as wiring cost, and a verifiable alternative source in task demands had been lacking.
The team trained recurrent networks on cognitive tasks and found that modularity rises as task load strains network capacity; incremental, task-by-task training produced the highest modularity and the best performance. Code and data are public on GitHub, and the findings so far hold only in simulation.