Robust Sequence Recall in Asymmetric Modern Hopfield Networks
Hamza Chaudhry, Dmitry Krotov, Cengiz Pehlevan · COSYNE 2023
Sequential memory is an essential attribute of natural and artificial intelligence that enables agents to encode, store, and retrieve complex sequences of stimuli and actions. Biologically plausible models of sequential memory have been proposed where recurrent neural networks are trained with temporal asymmetric Hebbian (TAH) rules. However, these networks have limited capacity, defined by the maximum length of sequence they can reliably recall, due to overlaps between stored memories reducing the signal to noise ratio. Inspired by recent work in Modern Hopfield Networks (MHN), we expand the
Sat, Mar 11, 2023