Rémi Monasson – Embedding of Low-Dimensional Attractor Manifolds

Rémi Monasson – Embedding of Low-Dimensional Attractor Manifolds by Neural Networks

#Rémi #Monasson #Embedding #LowDimensional #Attractor #Manifolds

“Institut des Hautes Études Scientifiques (IHÉS)”

Recurrent neural networks (RNN) have long been studied to explain how fixed-point attractors may emerge from noisy, high-dimensional dynamics. Recently, computational neuroscientists have devoted sustained efforts to understand how RNN could embed attractor manifolds of finite dimension, in…

source