Durability of Affordable Neural Networks against Damaging Neurons

Yoko UWATE  Yoshifumi NISHIO  Ruedi STOOP 

Publication
IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences  Vol.E92-A  No.2  pp.585-593
Publication Date: 2009/02/01
Online ISSN: 1745-1337
Print ISSN: 0916-8508
Type of Manuscript: PAPER
Category: Neural Networks and Bioengineering
Keyword: 
affordable neural networks,  durability,  back propagation learning, 

Full Text: PDF(1.2MB)

Summary: 
Durability describes the ability of a device to operate properly in imperfect conditions. 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. Whereas earlier we have shown that AfNNs can still generalize and learn, here we show that these networks are robust against damages occurring after the learning process has terminated. The results support the view that AfNNs embody the important feature of durability. In our contribution, we investigate the durability of the AfNN when some of the neurons in the hidden layer are damaged after the learning process.