hetero

hetero simulates recurrent neural networks whose neurons are heterogeneous in their time constants, benchmarks them on a family of temporal tasks, and quantifies how much of the task performance is explained by heterogeneity. Rate and spiking network dynamics (leaky integrate-and-fire), several stimulus sources, and a family of temporal tasks are driven from a single command-line entry point; fitted models can be compared against baselines and benchmarked on the reference computing systems used in the accompanying publication.