✦ LIBER ✦

Dynamical features simulated by recurrent neural networks

✍ Scribed by F. Botelho

Publisher: Elsevier Science
Year: 1999
Tongue: English
Weight: 96 KB
Volume: 12
Category: Article
ISSN: 0893-6080
DOI: 10.1016/s0893-6080(99)00026-x

No coin nor oath required. For personal study only.

✦ Synopsis

The evolution of two-dimensional neural network models with rank one connecting matrices and saturated linear transfer functions is dynamically equivalent to that of piecewise linear maps on an interval. It is shown that their iterative behavior ranges from being highly predictable, where almost every orbit accumulates to an attracting fixed point, to the existence of chaotic regions with cycles of arbitrarily large period.

📜 SIMILAR VOLUMES

Dynamical systems produced by recurrent

Dynamical systems produced by recurrent neural networks

✍ Masahiro Kimura; Ryohei Nakano 📂 Article 📅 2000 🏛 John Wiley and Sons 🌐 English ⚖ 237 KB 👁 2 views

Concerning the learning problems of recurrent neural networks (RNNs), this paper deals with the problem of approximating a dynamical system (DS) by an RNN as one extension of the problem of approximating trajectories by an RNN. In particular, we systematically investigate how an RNN can produce a DS

Dynamical control by recurrent neural ne

Dynamical control by recurrent neural networks through genetic algorithms

✍ Toru Kumagai; Mitsuo Wada; Ryoichi Hashimoto; Akio Utsugi 📂 Article 📅 1999 🏛 John Wiley and Sons 🌐 English ⚖ 135 KB 👁 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

Learning dynamical systems by recurrent

Learning dynamical systems by recurrent neural networks from orbits

✍ M. Kimura; R. Nakano 📂 Article 📅 1998 🏛 Elsevier Science 🌐 English ⚖ 253 KB

This paper investigates the problem of approximating a dynamical system (DS) by a recurrent neural network (RNN) as one extension of the problem of approximating orbits by an RNN. We systematically investigate how an RNN can produce a DS on the visible state space to approximate a given DS and as a

Control of nonlinear dynamical systems m

Control of nonlinear dynamical systems modeled by recurrent neural networks

✍ Michael Nikolaou; Vijaykumar Hanagandi 📂 Article 📅 1993 🏛 American Institute of Chemical Engineers 🌐 English ⚖ 323 KB 👁 2 views

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

Input/output linearization using dynamic

Input/output linearization using dynamic recurrent neural networks

✍ A. Delgado; C. Kambhampati; K. Warwick 📂 Article 📅 1996 🏛 Elsevier Science 🌐 English ⚖ 408 KB

This paper brings together two areas of research that have received considerable attention during the last years, namely feedback linearization and neural networks. A proposition that guarantees the Input/Output (I/O) linearization of nonlinear control affine systems with Dynamic Recurrent Neural N