Habituation based neural classifiers for spatio-temporal signals
نویسندگان
چکیده
Based on the habituation mechanism found in biological neural systems, novel dynamic neural networks are proposed for recognizing temporal patterns. The speciic task considered in this paper is the classiication of whale songs from passive SONAR data, but the networks are also readily applicable to other temporal pattern recognition problems. The fact that the networks designed operate dynamically is important, because it makes the goal of real time data analysis possible.
منابع مشابه
Habituation based neural networks for spatio-temporal classification1
A new class of neural networks is proposed for the dynamic classification of spatio-temporal signals. These networks are designed to classify signals of different durations, taking into account correlations among different signal segments. Such networks are applicable to SONAR and speech signal classification problems, among others. Network parameters are adapted based on the biologically obser...
متن کاملA Habituation Based Mechanism for Encoding Temporal Information in Artiicial Neural Networks
A novel neural network is proposed for the dynamic classiication of spatio-temporal signals. The network is designed to classify signals of diierent durations, taking into account correlations among diierent signal segments. Such a network is applicable to SONAR and speech signal classiication problems, among others. Network parameters are adapted based on the biologically observed habituation ...
متن کاملTwo Stage Habituation Based Neural
This article describes a novel neural network structure designed for the dynamic classiica-tion of spatio-temporal signals. The network is a two-stage structure consisting of a biologically motivated temporal encoding stage followed by a static neural classiier stage. The temporal encoding stage is based upon a simple biological learning mechanism known as habituation. This habituation based ne...
متن کاملA Habituation Based Neural Network for Spatio-temporal Classiication
A novel neural network is proposed for the dynamic classi cation of spatio-temporal signals. The network is designed to classify signals of di erent durations, taking into account correlations among di erent signal segments. Such a network is applicable to SONAR and speech signal classi cation problems, among others. Network parameters are adapted based on the biologically observed habituation ...
متن کاملHabituation based neural networks for spatio-temporal classification
A new class of neural networks are proposed for the dynamic classiication of spatio-temporal signals. These networks are designed to classify signals of diierent durations, taking into account correlations among diierent signal segments. Such networks are applicable to SONAR and speech signal classiication problems, among others. Network parameters are adapted based on the biologically observed...
متن کامل