Total least squares approach for fast learning in multilayer neural networks
Authors:
- R. ParisiRPR. Parisi
- E.D.D. ClaudioECE.D.D. Claudio
- G. OrlandiGOG. Orlandi
- 1 January 1995
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1, 474-477
Abstract
Classical methods for training feedforward neural networks are characterized by a number of shortcomings, first of all the slow rate of convergence and the occurrence of local minima. In this work a new learning algorithm is presented as a faster alternative to the Backpropagation method. The algorithm is based on the solution of a linearized system for each layer of the network performed by a block Total Least Squares technique. Simulation results are reported showing the high convergence speed of the new algorithm and its high degree of accuracyKeywords
This publication has 6 references indexed in Scilit:
- Fast learning process of multilayer neural networks using recursive least squares methodIEEE Transactions on Signal Processing, 1992
- A fast new algorithm for training feedforward neural networksIEEE Transactions on Signal Processing, 1992
- On the total least squares linear prediction method for frequency estimationIEEE Transactions on Acoustics, Speech, and Signal Processing, 1990
- ESPRIT-estimation of signal parameters via rotational invariance techniquesIEEE Transactions on Acoustics, Speech, and Signal Processing, 1989
- Accelerating the convergence of the back-propagation methodBiological Cybernetics, 1988
- Parallel Distributed Processing1986