A local training and pruning approach for neural networks |
| |
Authors: | Chang S J Leung C S Wong K W Sum J |
| |
Institution: | Department of Electronic Engineering, City University of Hong Kong, Kowloon Tong. |
| |
Abstract: | The training of neural networks using the extended Kalman filter (EKF) algorithm is plagued by the drawback of high computational complexity and storage requirement that may become prohibitive even for networks of moderate size. In this paper, we present a local EKF training and pruning approach that can solve this problem. In particular, the by-products obtained along with the local EKF training can be utilized to measure the importance of the network weights. Comparing with the original global approach, the proposed local EKF training and pruning approach results in a much lower computational complexity and storage requirement. Hence, it is more practical in solving real world problems. The performance of the proposed algorithm is demonstrated on one medium- and one large-scale problems, namely, sunspot data prediction and handwritten digit recognition. |
| |
Keywords: | |
本文献已被 PubMed 等数据库收录! |
|