𝔖 Bobbio Scriptorium
✦   LIBER   ✦

Complete controllability of continuous-time recurrent neural networks

✍ Scribed by Eduardo Sontag; Héctor Sussmann

Publisher
Elsevier Science
Year
1997
Tongue
English
Weight
549 KB
Volume
30
Category
Article
ISSN
0167-6911

No coin nor oath required. For personal study only.

📜 SIMILAR VOLUMES

Further results on controllability of re
Further results on controllability of recurrent neural networks
✍ E.D. Sontag; Y. Qiao 📂 Article 📅 1999 🏛 Elsevier Science 🌐 English ⚖ 134 KB

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 hy

A learning result for continuous-time re
A learning result for continuous-time recurrent neural networks
✍ Eduardo D. Sontag 📂 Article 📅 1998 🏛 Elsevier Science 🌐 English ⚖ 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

Approximation of dynamical systems by co
Approximation of dynamical systems by continuous time recurrent neural networks
✍ Ken-ichi Funahashi; Yuichi Nakamura 📂 Article 📅 1993 🏛 Elsevier Science 🌐 English ⚖ 431 KB

In this paper, we prove that any finite time trajectory of a given n-dimensional dynamical system can be approximately realized by the internal state of the output units of a continuous time recurrent neural network with n output units, some hidden units, and an appropriate initial condition. The es

A multilayer recurrent neural network fo
A multilayer recurrent neural network for solving continuous-time algebraic Riccati equations
✍ Jun Wang; Guang Wu 📂 Article 📅 1998 🏛 Elsevier Science 🌐 English ⚖ 373 KB

A multilayer recurrent neural network is proposed for solving continuous-time algebraic matrix Riccati equations in real time. The proposed recurrent neural network consists of four bidirectionally connected layers. Each layer consists of an array of neurons. The proposed recurrent neural network is