Convergent on-line algorithms for supervised learning in neural networks

Authors:
L. Grippo
Affiliations:
Dipartimento di Inf. e Sistemistica, Rome Univ., Italy
Venue:
IEEE Transactions on Neural Networks
Year:
2000

Citing 0
Cited 6

Deterministic convergence of an online gradient method for neural networks

Journal of Computational and Applied Mathematics - Selected papers of the international symposium on applied mathematics, August 2000, Dalian, China
An Incremental Method for Solving Convex Finite Min-Max Problems

Mathematics of Operations Research
The extended Ritz method for functional optimization: overview and applications to single-person and team optimal decision problems

Optimization Methods & Software
On solving the Lagrangian dual of integer programs via an incremental approach

Computational Optimization and Applications
Boundedness and convergence of online gradient method with penalty for feedforward neural networks

IEEE Transactions on Neural Networks
Management of water resource systems in the presence of uncertainties by nonlinear approximation techniques and deterministic sampling

Computational Optimization and Applications

Quantified Score

Hi-index	0.00

Visualization

Abstract

We define online algorithms for neural network training, based on the construction of multiple copies of the network, which are trained by employing different data blocks. It is shown that suitable training algorithms can be defined, in a way that the disagreement between the different copies of the network is asymptotically reduced, and convergence toward stationary points of the global error function can be guaranteed. Relevant features of the proposed approach are that the learning rate must be not necessarily forced to zero and that real-time learning is permitted.