Title :
Noise injection into inputs in sparsely connected Hopfield and winner-take-all neural networks
Author_Institution :
Sch. of Comput. & Math., Deakin Univ., Clayton, Vic., Australia
fDate :
9/1/1997 12:00:00 AM
Abstract :
In this paper, we show that noise injection into inputs in unsupervised learning neural networks does not improve their performance as it does in supervised learning neural networks. Specifically, we show that training noise degrades the classification ability of a sparsely connected version of the Hopfield neural network, whereas the performance of a sparsely connected winner-take-all neural network does not depend on the injected training noise
Keywords :
Hopfield neural nets; noise; unsupervised learning; Hopfield neural network; injected training noise; neural networks; sparsely connected; unsupervised learning; winner-take-all neural network; Active noise reduction; Artificial neural networks; Degradation; Hopfield neural networks; Intelligent networks; Neural networks; Neurons; Signal processing; Supervised learning; Unsupervised learning;
Journal_Title :
Systems, Man, and Cybernetics, Part B: Cybernetics, IEEE Transactions on
DOI :
10.1109/3477.623239
