J. Marco

The paper demonstrates a biologically plausible model that memorizes and recalls sequences using a sparse coding scheme and Dale's law constraints, achieving perfect recall with a modest latent size.

The paper identifies a signed-XOR connectomic motif that enables directional error signaling in neural circuits, showing its enrichment in C. elegans, Drosophila, and mouse visual cortex.

This paper investigates whether a signed error derived from an XOR-based neuronal mechanism can serve as a learning signal in a binary autoencoder, showing improved reconstruction accuracy compared to traditional methods.