Entropy learning in neural network

• Main Authors: Geok, See Ng, Shi, Daming, Abdul Rahman, Abdul Wahab, Singh, H.
• Format: Article
• Language: English
• Published: ASEAN Committee on Science and Technology 2003
• Subjects: T Technology (General)
• Online Access: http://irep.iium.edu.my/38199/1/ENTROPY_LEARNING_IN_NEURAL_NETWORK.pdf; http://irep.iium.edu.my/38199/; http://astnet.asean.org/index.php?name=Main&file=content&cid=32
• Institution: Universiti Islam Antarabangsa Malaysia

In this paper, entropy term is used in the learning phase of a neural network. As learning progresses, more hidden nodes get into saturation. The early creation of such hidden nodes may impair generalisation. Hence entropy approach is proposed to dampen the early creation of such nodes. The entropy learning also helps to increase the importance of relevant nodes while dampening the less important nodes. At the end of learning, the less important nodes can then be eliminated to reduce the memory requirements of the neural network.