首页 | 本学科首页   官方微博 | 高级检索  
     


Adaptive networks for physical modeling
Authors:Nicolas Szilas  Claude Cadoz
Affiliation:

a ACROE-CLIPS-IMAG, 46 avenue Félix Viallet, 38031 Grenoble Cedex, France

b LEIBNIZ-IMAG, 46 avenue Félix Viallet, 38031 Grenoble Cedex, France

Abstract:This paper presents an original link between neural networks theory and mechanical modeling networks. The problem is to find the parameters characterizing mechanical structures in order to reproduce given mechanical behaviors. Replacing “neural” units with mechanically based units and applying classical learning algorithms dedicated to supervised dynamic networks to these mechanical networks allows us to find the parameters for a physical model. Some new variants of real-time recurrent learning (RTRL) are also introduced, based on mechanical principles.

The notion of interaction during learning is discussed at length and the results of tests are presented. Instead of the classical {machine learning system, environment} pair, we propose to study the {machine learning system, human operator, environment} triplet.

Experiments have been carried out in simulated scenarios and some original experiments with a force-feedback device are also described.

Keywords:Recurrent networks   Physical modeling   Active learning
本文献已被 ScienceDirect 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号