Title :
A novel approach to the convergence of neural networks for signal processing
Author :
Liu, Ruey-wen ; Huang, Yih-fang ; Ling, Xie-Ting
Author_Institution :
Dept. of Electr. Eng., Notre Dame Univ., IN, USA
fDate :
3/1/1995 12:00:00 AM
Abstract :
A novel deterministic approach to the convergence analysis of (stochastic) learning algorithms is presented. The link between the two is the new concept of time-average invariance, which is a property of deterministic signals but resembles that of stochastic signals which are ergodic and stationary
Keywords :
neural nets; signal processing; stochastic processes; unsupervised learning; convergence analysis; deterministic approach; neural networks; signal processing; stochastic learning algorithms; stochastic signals; time-average invariance; Active filters; Algorithm design and analysis; Circuit analysis; Convergence; Equations; Neural networks; Signal analysis; Signal processing; Signal processing algorithms; Stochastic processes;
Journal_Title :
Circuits and Systems I: Fundamental Theory and Applications, IEEE Transactions on
