3 papers
cond-mat.dis-nn2026
Storing Infinite Dynamical Attractors in Nonreciprocal Associative Neural Networks
Miguel Aguilera, Daniele De Martino
We develop a dynamical mean-field theory for nonreciprocal associative networks that store an extensive number of dynamical attractors, from limit cycles to strange attractors. Usi…
cond-mat.dis-nn2024
Explosive neural networks via higher-order interactions in curved statistical manifolds
Miguel Aguilera, Pablo A. Morales, Fernando E. Rosas +1
Higher-order interactions underlie complex phenomena in systems such as biological and artificial neural networks, but their study is challenging due to the scarcity of tractable m…
cond-mat.dis-nn2024
Dynamical Mean-Field Theory of Self-Attention Neural Networks
Ángel Poc-López, Miguel Aguilera
Transformer-based models have demonstrated exceptional performance across diverse domains, becoming the state-of-the-art solution for addressing sequential machine learning problem…