615 citations · 661 across the 9 of their papers we have counts for
4 papers · 1 filter
Ideomotor feedback control in a recurrent neural network
Mathieu Galtier
The architecture of a neural network controlling an unknown environment is presented. It is based on a randomly connected recurrent neural network from which both perception and ac…
Regular graphs maximize the variability of random neural networks
Gilles Wainrib, Mathieu Galtier
In this work we study the dynamics of systems composed of numerous interacting elements interconnected through a random weighted directed graph, such as models of random neural net…
A local Echo State Property through the largest Lyapunov exponent
Mathieu Galtier, Gilles Wainrib
Echo State Networks are efficient time-series predictors, which highly depend on the value of the spectral radius of the reservoir connectivity matrix. Based on recent results on t…
Relative entropy minimizing noisy non-linear neural network to approximate stochastic processes
Mathieu N. Galtier, Camille Marini, Gilles Wainrib +1
A method is provided for designing and training noise-driven recurrent neural networks as models of stochastic processes. The method unifies and generalizes two known separate mode…