Title :
How to maintain information content in artificial neural networks with coherence adaptation
Author :
Shahjahan, Md ; Asaduzzaman, Md ; Murase, K.
Author_Institution :
Dept. of EEE, Khulna Univ. of Eng. & Technol. (KUET), Khulna
Abstract :
This paper presents a learning approach called adaptive coherence scheme (CAS) that adaptively reduces information on input patterns in hidden layer(s) of a neural network. The hidden units in a neural network store information continuously during training session. As a result the network becomes extremely familiar with every details of input patterns. This is not desirable in training. Therefore, we attempt to limit this information automatically with a regularization function consisting of activations of hidden units. We proposed standard coherence learning (SCL) where a constant coherence strength was used in order to solve the problem. Here, we attempt to develop a coherence adaptation scheme in order to maintain small amount of information in the network automatically. We have applied the algorithm to the breast cancer classification and Mackey-Glass chaotic time series prediction problems with single and double hidden layered networks. The results show that the network maintains small amount of information with good classification and prediction accuracies.
Keywords :
chaos; image classification; medical image processing; neural nets; time series; Mackey-Glass chaotic time series prediction problems; artificial neural networks; breast cancer classification; coherence adaptation; double hidden layered networks; information content; single hidden layered networks; standard coherence learning; training session; Artificial neural networks; Biological neural networks; Classification algorithms; Decorrelation; Evolutionary computation; Humans; Minimization methods; Neural networks; Neurons; Robustness;
Conference_Titel :
Neural Networks, 2008. IJCNN 2008. (IEEE World Congress on Computational Intelligence). IEEE International Joint Conference on
Conference_Location :
Hong Kong
Print_ISBN :
978-1-4244-1820-6
Electronic_ISBN :
1098-7576
DOI :
10.1109/IJCNN.2008.4634076