Pruned Feed-forward Networks for Efficient Implementation of Multiple FIR Filters with Arbitrary Frequency Responses |
| |
Authors: | Ki-Hwan Ahn Yoon Kyung Choi Soo-Young Lee |
| |
Affiliation: | (1) Computation and Neural Systems Laboratory, Department of Electrical Engineering, Korea, Advanced Institute of Science and Technology, 373–1 Kusong-dong, Yusong-gu, Taejon, 305–701, Korea |
| |
Abstract: | A new algorithm is presented for efficient implementation of multiple FIR filters in real-time applications. We introduce an analogy between the multiple FIR filters and linear feed-forward networks, and show how the FIR filters with any frequency characteristics may be designed by a learning algorithm of the network with proper choice of training patterns. Starting from a fully-connected feed-forward architecture, more efficient network architectures may be obtainable by pruning connection weights with minor contributions. For demonstration we design feed-forward networks for 16 bandpass cochlear filters with much less connection weights and moderate performance degradation. |
| |
Keywords: | cochlear filter error backpropatation feed-forward network FIR filter network complexity pruning reduced multiplication |
本文献已被 SpringerLink 等数据库收录! |
|