On stable learning of block-diagonal recurrent neural networks, Part 1: the RENNCOM algorithm

@article{Mastorocostas2004OnSL,
title={On stable learning of block-diagonal recurrent neural networks, Part 1: the RENNCOM algorithm},
author={P. A. Mastorocostas and J. B. Theocharis},
journal={2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541)},
year={2004},
volume={2},
pages={815-820 vol.2}
}

A novel learning algorithm, the RENNCOM (recurrent neural network constrained optimization method), is suggested in this paper, for training block-diagonal recurrent neural networks. The training task is formulated as a constrained optimization problem, whose objective is twofold: (i) minimization of an error measure, leading to successful approximation of the input/output mapping and (ii) optimization of an additional functional, which aims at ensuring network stability throughout the learning… CONTINUE READING

A Steepest - Ascent Method for Solving Optimum Programming hablcms Globally Asymptotical Stability of Discrete - Time Analog Neural Networks : IEEE Trans