Title :
Dynamic backpropagation algorithm for neural network controlled resonator-bank architecture
Author :
Sztipanovits, Janos
Author_Institution :
Dept. of Electr. Eng., Vanderbilt Univ., Nashville, TN, USA
fDate :
2/1/1992 12:00:00 AM
Abstract :
An adaptive processing system that consists of a resonator-based digital filter and a neural network is presented. The filter section realizes the dynamics of the adaptive system, while the transfer characteristics are controlled by the neural network. The author focuses on online training algorithms that can create an association between features of the input signal of the neural network and dynamic responses of the digital filter. A dynamic back propagation algorithm is derived for training the network in closed-loop configurations, when a feedback path exists between the output of the digital filter section and inputs to the neural network. Simulation results show that the neural network controlled resonator-bank architecture is computationally feasible and can be used as a general building block in a wide range of identification and control problems
Keywords :
adaptive filters; closed loop systems; digital filters; dynamic response; feedback; filtering and prediction theory; learning systems; neural nets; resonators; adaptive processing system; closed-loop configurations; digital filter; dynamic back propagation algorithm; dynamic responses; feedback path; neural network; online training algorithms; resonator-bank architecture; transfer characteristics; Adaptive control; Adaptive filters; Adaptive systems; Backpropagation algorithms; Control systems; Digital filters; Heuristic algorithms; Neural networks; Programmable control; Resonator filters;
Journal_Title :
Circuits and Systems II: Analog and Digital Signal Processing, IEEE Transactions on