Robustness of Two-Layered Feedforward Neural Network

Abstract

Abstract:In this paper a two-layer feedforward network is studied, a network that stores an association between two sequences in the two layers. Our work shows that neuronal sequences in one area can robustly trigger sequences in the second area if the association between the sequences is stored in the network. A more detailed incorporation into the biological aspects of neural network in the network dynamics may help to improve neutral networks in engineering applications.