Title :
Adaptive processing with neural network controlled resonator-banks
Author :
Sztipanovits, Janos
Author_Institution :
Dept. of Electr. Eng., Vanderbilt Univ., Nashville, TN, USA
fDate :
11/1/1990 12:00:00 AM
Abstract :
A structurally adaptive processing system that can dynamically change its transfer characteristics as a response to changes in the environment is described. The neural network controlled resonator-bank architecture consists of two main components, a resonator-bank filter structure and a neural network that controls the transfer characteristics of the filter. The architecture offers an attractive alternative for the approximation of time-variant nonlinear dynamics having a finite number of stable operating points with quasi-linear characteristics
Keywords :
adaptive filters; digital filters; filtering and prediction theory; neural nets; resonators; signal processing; approximation; neural network controlled resonator-banks; quasi-linear characteristics; resonator-bank filter structure; stable operating points; structurally adaptive processing system; time-variant nonlinear dynamics; training methods; transfer characteristics; Adaptive control; Adaptive systems; Circuit theory; Circuits and systems; Control systems; Filters; Network synthesis; Neural networks; Programmable control; Reflection;
Journal_Title :
Circuits and Systems, IEEE Transactions on
