CONSTRUCTING BIOLOGICALLY CONSTRAINED RNNS VIA DALE'S BACKPROP AND TOPOLOGICALLY-INFORMED PRUNING.

ABSTRACT: Recurrent neural networks (RNNs) have emerged as a prominent tool for modeling cortical function, and yet their conventional architecture is lacking in physiological and anatomical fidelity. In particular, these models often fail to incorporate two crucial biological constraints: i) Dale's law, i.e., sign constraints that preserve the "type" of projections from individual neurons, and ii) Structured connectivity motifs, i.e., highly sparse yet defined connections amongst various neuronal populations. Both constraints are known to impair learning performance in artificial neural networks, especially when trained to perform complicated tasks; but as modern experimental methodologies allow us to record from diverse neuronal populations spanning multiple brain regions, using RNN models to stud

SUBMITTER: Balwani AH 

PROVIDER: S-EPMC11760306 | biostudies-literature | 2025 Jan

REPOSITORIES: biostudies-literature