𝔖 Bobbio Scriptorium
✦   LIBER   ✦

Further results on controllability of recurrent neural networks

✍ Scribed by E.D. Sontag; Y. Qiao

Publisher
Elsevier Science
Year
1999
Tongue
English
Weight
134 KB
Volume
36
Category
Article
ISSN
0167-6911

No coin nor oath required. For personal study only.

✦ Synopsis

This paper studies controllability properties of recurrent neural networks. The new contributions are: (1) an extension of a previous result to a slightly di erent model, (2) a formulation and proof of a necessary and su cient condition, and (3) an analysis of a low-dimensional case for which the hypotheses made in previous work do not apply.

πŸ“œ SIMILAR VOLUMES

A learning result for continuous-time re
A learning result for continuous-time recurrent neural networks
✍ Eduardo D. Sontag πŸ“‚ Article πŸ“… 1998 πŸ› Elsevier Science 🌐 English βš– 117 KB

The following learning problem is considered, for continuous-time recurrent neural networks having sigmoidal activation functions. Given a "black box" representing an unknown system, measurements of output derivatives are collected, for a set of randomly generated inputs, and a network is used to ap

Adaptive recurrent neural network contro
Adaptive recurrent neural network control of biological wastewater treatment
✍ Ieroham S. Baruch; Petia Georgieva; Josefina Barrera-Cortes; Sebastiao Feyo de A πŸ“‚ Article πŸ“… 2004 πŸ› John Wiley and Sons 🌐 English βš– 595 KB

Three adaptive neural network control structures to regulate a biological wastewater treatment process are introduced: indirect, inverse model, and direct adaptive neural control. The objective is to keep the concentration of the recycled biomass proportional to the influent flow rate in the presenc

Dynamical control by recurrent neural ne
Dynamical control by recurrent neural networks through genetic algorithms
✍ Toru Kumagai; Mitsuo Wada; Ryoichi Hashimoto; Akio Utsugi πŸ“‚ Article πŸ“… 1999 πŸ› John Wiley and Sons 🌐 English βš– 135 KB πŸ‘ 2 views

In this study we composed a recurrent neural network learning controller and applied it to the swinging up and stabilization problem of the inverted pendulum. A recurrent neural network was trained by a genetic algorithm which had an internal copy operator or inter-individual copy operator. An appro

Adaptive recurrent fuzzy neural networks
Adaptive recurrent fuzzy neural networks for active noise control
✍ Qi-Zhi Zhang; Woon-Seng Gan; Ya-li Zhou πŸ“‚ Article πŸ“… 2006 πŸ› Elsevier Science 🌐 English βš– 480 KB

This paper discussed nonlinear active noise control (ANC). Some adaptive nonlinear noise control approaches using recurrent fuzzy neural networks (RFNNs) were derived. The proposed RFNNs were feed-forward fuzzy neural networks (NNs) with different local feedback connections that are used to construc