Summary
|
For Full-Text PDF, please login, if you are a member of IEICE, or go to Pay Per View on menu list, if you are a nonmember of IEICE. |
|
Design of FIR Digital Filters Using Hopfield Neural Network Yue-Dar JOU Fu-Kun CHEN Publication IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences Vol.E90-A No.2 pp.439-447 Publication Date: 2007/02/01 Online ISSN: 1745-1337 DOI: 10.1093/ietfec/e90-a.2.439 Print ISSN: 0916-8508 Type of Manuscript: PAPER Category: Digital Signal Processing Keyword: filter design, FIR, Hopfield neural network, Lyapunov energy function, Full Text: PDF(384.1KB)>>
Summary: This paper is intended to provide an alternative approach for the design of FIR filters by using a Hopfield Neural Network (HNN). The proposed approach establishes the error function between the amplitude response of the desired FIR filter and the designed one as a Lyapunov energy function to find the HNN parameters. Using the framework of HNN, the optimal filter coefficients can be obtained from the output state of the network. With the advantages of local connectivity, regularity and modularity, the architecture of the proposed approach can be applied to the design of differentiators and Hilbert transformer with significantly reduction of computational complexity and hardware cost. As the simulation results illustrate, the proposed neural-based method is capable of achieving an excellent performance for filter design. | ||||||||||
| ||||||||||