Title :
Analysis of a perceptron learning algorithm with momentum updating
Author :
Shynk, John J. ; Roy, Sumit
Author_Institution :
Dept. of Electr. & Comput. Eng., California Univ., Santa Barbara, CA, USA
Abstract :
An analysis is presented of the stationary points of an adaptive algorithm that adjusts the perceptron weights. This algorithm is identical in form to the least-mean-square (LMS) algorithm, except that a hard limiter is incorporated at the output of the summer. In addition, a momentum term is included in the weight update; this modified algorithm is referred to as the momentum LMS (MLMS) algorithm. It is shown that the stationary points of the MLMS algorithm are not unique; they depend not only on the statistics of the input and the desired response, but also on the specific values used for the algorithm convergence parameters, the step size and convergence constant
Keywords :
learning systems; least squares approximations; neural nets; MLMS algorithm; adaptive algorithm; hard limiter; momentum least mean squares algorithm; momentum updating; neural network; perceptron learning algorithm; stationary points; Adaptive algorithm; Algorithm design and analysis; Computer networks; Convergence; Feedforward neural networks; Feedforward systems; Least squares approximation; Multi-layer neural network; Multilayer perceptrons; Neural networks; Statistics; Vectors;
Conference_Titel :
Acoustics, Speech, and Signal Processing, 1990. ICASSP-90., 1990 International Conference on
Conference_Location :
Albuquerque, NM
DOI :
10.1109/ICASSP.1990.115643
