Title :
Design of equiripple linear phase FIR filters by feedback neural networks
Author :
Bhattacharya, D. ; Antoniou, A.
Author_Institution :
Dept. of Electr. & Comput. Eng., Victoria Univ., BC, Canada
Abstract :
A Hopfield-type neural network is proposed for the design of equiripple FIR digital filters. A weighted least-squares error function is minimized in an iterative fashion and weights are updated at the end of each iteration until the desired accuracy is achieved. The network is simulated and an example is included to show that this is an efficient way of solving the approximation problem and has a high potential for implementation in analog VLSI
Keywords :
FIR filters; Hopfield neural nets; delay circuits; digital filters; filtering theory; iterative methods; least mean squares methods; Hopfield-type neural network; equiripple linear phase FIR filters; feedback neural networks; weighted least-squares error function; Computer errors; Digital filters; Error correction; Finite impulse response filter; Frequency; Hopfield neural networks; Neural networks; Neurofeedback; Neurons; Nonlinear filters; Very large scale integration;
Conference_Titel :
Circuits and Systems, 1995., Proceedings., Proceedings of the 38th Midwest Symposium on
Conference_Location :
Rio de Janeiro
Print_ISBN :
0-7803-2972-4
DOI :
10.1109/MWSCAS.1995.504510
