Title :
Effectiveness of artificial neural network with time-varying coupling system
Author :
Uwate, Yoko ; Nishio, Yusuke
Author_Institution :
Dept. of Electr. & Electron. Eng., Tokushima Univ., Tokushima, Japan
Abstract :
We have recently proposed a novel neural network structure called an “Affordable Neural Network” (AfNN), in which affordable neurons of the hidden layer are considered as the elements responsible for the robustness property as is observed in human brain function. In this study, we investigate the mechanism of learning process of the AfNN to make clear the reason of that the AfNNs can perform well for learning and generalization abilities and operate as usually against damaging neurons.
Keywords :
brain; neural nets; robust control; time-varying systems; AfNN; affordable neural network; artificial neural network; generalization abilities; human brain function; learning abilities; neural network structure; neurons; robustness property; time-varying coupling system; Artificial neural networks; Biological neural networks; Fault tolerance; Fault tolerant systems; Neurons; Neuroscience; Pattern recognition;
Conference_Titel :
Circuits and Systems (ISCAS), 2014 IEEE International Symposium on
Conference_Location :
Melbourne VIC
Print_ISBN :
978-1-4799-3431-7
DOI :
10.1109/ISCAS.2014.6865557