Paper Info
Title
Distributed deterministic temporal information propagated by feedforward neural networks
Abstract
A ten layers feedforward network characterized by diverging/ converging patterns of projection between successive layers is activated by an external spatio-temporal input pattern fed to layer 1 in presence of stochastic background activities fed to all layers. We used three dynamical systems to derive the external input spike trains including the temporal information, and two types of neuron models for the network, i.e. either a simple spiking neuron (SSN) or a multiple-timescale adaptive threshold neuron (MAT). We observed an unimodal integration effect as a function of the order of the layers and confirmed that the MAT model is likely to be more efficient in integrating and transmitting the temporal structure embedded in the external input.
Year
DOI
Venue
2011
10.1007/978-3-642-21735-7_32
ICANN (1)
Keywords
Field
DocType
feedforward neural network,temporal information,neuron model,external spatio-temporal input pattern,layers feedforward network,external input spike train,temporal structure,multiple-timescale adaptive threshold neuron,mat model,deterministic temporal information,simple spiking neuron,external input
Feedforward neural network,Threshold potential,Computer science,Dynamical systems theory,Artificial intelligence,Synfire chain,Machine learning,Feed forward
Conference
Volume
ISSN
Citations 
6791
0302-9743
0
PageRank 
References 
Authors
0.34
7
2
Name
Order
Citations
PageRank
Yoshiyuki Asai1307.56
Alessandro E . P. Villa234853.26