Title :
Adaptive training of multilayer neural networks using a least squares estimation technique
Author :
Kollias, Stefanos ; Anastassiou, Dimitris
Author_Institution :
Dept. of Electr. Eng., Columbia Univ., New York, NY, USA
Abstract :
A technique is developed for the training of artificial neural networks, using a modification of the Marquardt-Levenberg optimization technique. An adaptive choice of the convergence rate factor mu , based on the contribution of each neuron in the minimization of the error function, is presented that can be very useful in handling the problem of local minima of the error function. The proposed algorithm is more powerful but also more elaborate than backpropagation. Moreover, it can be shown that in some applications its computational complexity can be made similar to that of backpropagation by using fast implementations of the least-squares method.<>
Keywords :
adaptive systems; artificial intelligence; least squares approximations; neural nets; optimisation; Marquardt-Levenberg optimization; adaptive training; artificial intelligence; backpropagation; computational complexity; convergence rate factor; error function; least squares estimation; multilayer neural networks; neuron; Adaptive systems; Artificial intelligence; Least squares methods; Neural networks; Optimization methods;
Conference_Titel :
Neural Networks, 1988., IEEE International Conference on
Conference_Location :
San Diego, CA, USA
DOI :
10.1109/ICNN.1988.23870