Recursive least squares approach to learning in recurrent neural networks
Authors:
- R. ParisiRPR. Parisi
- E.D. Di ClaudioECE.D. Di Claudio
- A. RapagnettaARA. Rapagnetta
- G. OrlandiGOG. Orlandi
- 1 January 1996
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 2, 1350-1354
Abstract
This paper presents a new approach to learning in recurrent neural networks, based on the descent of the error functional in the space of the linear outputs of the neurons (neuron space approach). At each step of the learning process a linear system is solved for the weights using a Recursive Least Squares technique. This approach, with respect to traditional gradient-based algorithms, guarantees better performances from the point of view of both the speed of convergence and the numerical robustnessKeywords
This publication has 4 references indexed in Scilit:
- Total least squares approach for fast learning in multilayer neural networks1995
- A fast new algorithm for training feedforward neural networksIEEE Transactions on Signal Processing, 1992
- An Efficient Gradient-Based Algorithm for On-Line Training of Recurrent Network TrajectoriesNeural Computation, 1990
- Identification and control of dynamical systems using neural networksIEEE Transactions on Neural Networks, 1990