Abstract
We propose a neural network to synthesize an arbitrary FIR filter in a least square sense. The network can evolve to its steady-states or equilibrium points from any initial state in the magnitude of the circuit's time constant. Under the steady-state, the output of the network is just our designed FIR filter coefficient if a real, symmetric, and positive-definite matrix calculated by the design specifications is directly used as the synaptic strength matrix.
Similar content being viewed by others
References
D.W. Tank and J.J. Hopfield, “Simple 'neural' optimization networks: An A/D converter, signal decision circuit, and a linear programming circuit,” IEEE Trans., 1986, CAS-33,(5), pp. 533–541.
P.P. Vaidyanathan and T.Q. Nguyen, “Eigenfilters: A new approach to least squares FIR filter design and applications including Nyquist filters,” IEEE Trans., 1987, CAS-34,(1), pp. 11–23.
M. Forti, S. Manetti and M. Marini, “Neural network for adaptive FIR filtering”, Electronics Letters, 1990, Vol. 26,(14), pp. 1018–1019.
D. Bhattacharya and A. Antoniou, “Real-time synthesis of FIR filters in frequency domain by feedback neural nets”, Proc. of the 27th MSCAS, 1994.
Y. Tan and Z. Y. He, “A neural network structure for determination of minimum eigenvalue and its corresponding eigenvector of a symmetrical matrix”, Proc. of 1995 IEEE International Conference of Neural Network Signal Processing (ICNNSP'95), China, Vol. I, pp. 512–516.
Y. Tan and Z. Y. He, “Neural network approaches for the extraction of the eigenstructure,” Neural Networks for Signal Processing VI - Proceedings of the 1996 IEEE Workshop, Kyoto, Japan, Septembert, 1996. pp. 23–32.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Tan, Y., He, Z. Arbitrary FIR Filter Synthesis Using a Neural Network. Neural Processing Letters 8, 9–13 (1998). https://doi.org/10.1023/A:1009608911373
Issue Date:
DOI: https://doi.org/10.1023/A:1009608911373