AI RESEARCH

Beyond Fixed Points: Superpolynomial Capacity of Asymmetric Hopfield Networks

arXiv CS.LG

ArXi:2605.24611v1 Announce Type: new Classical Hopfield networks are limited to static patterns due to symmetric weights, whereas asymmetric networks can encode temporal sequences via limit-cycle attractors. Achieving high-capacity storage of long sequences in classical synchronous asymmetric networks, however, has remained a challenge.