Anjana Santhosh

Task-dependence of network-to-network variability in learning, performance, and dynamics of heterogeneous recurrent networks

The paper investigates how task-dependent variability arises in artificial recurrent networks with intrinsic heterogeneities, showing functional degeneracy and non-monotonic relationships between heterogeneity, task demands, and performance.

Diversity in the impact of heterogeneities on recurrent networks performing a cognitive task

This study assesses how different levels of heterogeneity affect the performance and dynamics of recurrent neural networks trained on a cognitive task.