๐”– Bobbio Scriptorium
โœฆ   LIBER   โœฆ

Dynamical control by recurrent neural networks through genetic algorithms

โœ Scribed by Toru Kumagai; Mitsuo Wada; Ryoichi Hashimoto; Akio Utsugi

Publisher
John Wiley and Sons
Year
1999
Tongue
English
Weight
135 KB
Volume
13
Category
Article
ISSN
0890-6327

No coin nor oath required. For personal study only.

โœฆ Synopsis

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 appropriate controller was acquired in a recurrent neural network by training with a simple evaluation function. The recurrent neural network acquired two completely di!erent rules for swinging up and stabilization of a pendulum. It outputted these two rules continuously so that swinging up and stabilization of a pendulum was realized. Internal copy and inter-individual copy accelerated learning e!ectively by copying a part of a chromosome.

๐Ÿ“œ SIMILAR VOLUMES

Dynamical systems produced by recurrent
Dynamical systems produced by recurrent neural networks
โœ Masahiro Kimura; Ryohei Nakano ๐Ÿ“‚ Article ๐Ÿ“… 2000 ๐Ÿ› John Wiley and Sons ๐ŸŒ English โš– 237 KB ๐Ÿ‘ 1 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

Global optimization of a dryer by using
Global optimization of a dryer by using neural networks and genetic algorithms
โœ A. Hugget; P. Sรฉbastian; J.-P. Nadeau ๐Ÿ“‚ Article ๐Ÿ“… 1999 ๐Ÿ› American Institute of Chemical Engineers ๐ŸŒ English โš– 162 KB ๐Ÿ‘ 2 views

For many optimum design problems, the objectiยฎe function is the result of a complex numerical code and may not be differentiable and explicit. The first aim is to propose a way of solยฎing such complexity on an example problem. A noยฎel and global strategy inยฎolยฎing artificial neural networks and a ge

Control of structural seismic response b
Control of structural seismic response by self-recurrent neural network (SRNN)
โœ He, Yu-Ao; Wu, Jianjun ๐Ÿ“‚ Article ๐Ÿ“… 1998 ๐Ÿ› John Wiley and Sons ๐ŸŒ English โš– 108 KB ๐Ÿ‘ 1 views

A new paradigm called self-recurrent neural network (SRNN) is proposed. Two SRNNs are utilized in a control system, one as an emulator and the other as a controller. To guarantee convergence and for faster learning, an approach using adaptive learning rate is developed by Lyapunov function. Finally,