A simple mechanical system for studying adaptive oscillatory neural networks

Guillaume Jouffroy, Jerome Jouffroy

Publikation: Konferencebidrag uden forlag/tidsskriftPaperForskningpeer review

Resumé

Central Pattern Generators (CPG) are oscillatory systems that are responsible for generating rhythmic patterns at the origin of many biological activities such as for example locomotion or digestion. These systems are generally modelled as recurrent neural networks whose parameters are tuned so that the network oscillates in a suitable way, this tuning being a non trivial task. It also appears that the link with the physical body that these oscillatory entities control has a fundamental importance, and it seems that most bodies used for experimental validation in the literature (walking robots, lamprey model, etc.) might be too complex to study. In this paper, we use a comparatively simple mechanical system, the nonholonomic vehicle referred to as the Roller-Racer, as a means towards testing different learning strategies for an Recurrent Neural Network-based (RNN) controller/guidance system. After a brief description of the Roller-Racer, we present as a preliminary study an RNN-based feed-forward controller whose parameters are obtained through the well-known teacher forcing learning algorithm, extended to learn signals with a continuous component.

OriginalsprogEngelsk
Publikationsdato2006
StatusUdgivet - 2006
BegivenhedIEEE Int. Conference on Systems, Man, and Cybernetics (SMC'06) - Taipei, Taiwan
Varighed: 24. aug. 2010 → …

Konference

KonferenceIEEE Int. Conference on Systems, Man, and Cybernetics (SMC'06)
LandTaiwan
ByTaipei
Periode24/08/2010 → …

Fingeraftryk

Recurrent neural networks
Neural networks
Controllers
Bioactivity
Learning algorithms
Tuning
Robots
Testing

Citer dette

Jouffroy, G., & Jouffroy, J. (2006). A simple mechanical system for studying adaptive oscillatory neural networks. Afhandling præsenteret på IEEE Int. Conference on Systems, Man, and Cybernetics (SMC'06), Taipei, Taiwan.
Jouffroy, Guillaume ; Jouffroy, Jerome. / A simple mechanical system for studying adaptive oscillatory neural networks. Afhandling præsenteret på IEEE Int. Conference on Systems, Man, and Cybernetics (SMC'06), Taipei, Taiwan.
@conference{0fc906103df411dda26c000ea68e967b,
title = "A simple mechanical system for studying adaptive oscillatory neural networks",
abstract = "Central Pattern Generators (CPG) are oscillatory systems that are responsible for generating rhythmic patterns at the origin of many biological activities such as for example locomotion or digestion. These systems are generally modelled as recurrent neural networks whose parameters are tuned so that the network oscillates in a suitable way, this tuning being a non trivial task. It also appears that the link with the physical body that these oscillatory entities control has a fundamental importance, and it seems that most bodies used for experimental validation in the literature (walking robots, lamprey model, etc.) might be too complex to study. In this paper, we use a comparatively simple mechanical system, the nonholonomic vehicle referred to as the Roller-Racer, as a means towards testing different learning strategies for an Recurrent Neural Network-based (RNN) controller/guidance system. After a brief description of the Roller-Racer, we present as a preliminary study an RNN-based feed-forward controller whose parameters are obtained through the well-known teacher forcing learning algorithm, extended to learn signals with a continuous component.",
author = "Guillaume Jouffroy and Jerome Jouffroy",
year = "2006",
language = "English",
note = "null ; Conference date: 24-08-2010",

}

Jouffroy, G & Jouffroy, J 2006, 'A simple mechanical system for studying adaptive oscillatory neural networks' Paper fremlagt ved IEEE Int. Conference on Systems, Man, and Cybernetics (SMC'06), Taipei, Taiwan, 24/08/2010, .

A simple mechanical system for studying adaptive oscillatory neural networks. / Jouffroy, Guillaume; Jouffroy, Jerome.

2006. Afhandling præsenteret på IEEE Int. Conference on Systems, Man, and Cybernetics (SMC'06), Taipei, Taiwan.

Publikation: Konferencebidrag uden forlag/tidsskriftPaperForskningpeer review

TY - CONF

T1 - A simple mechanical system for studying adaptive oscillatory neural networks

AU - Jouffroy, Guillaume

AU - Jouffroy, Jerome

PY - 2006

Y1 - 2006

N2 - Central Pattern Generators (CPG) are oscillatory systems that are responsible for generating rhythmic patterns at the origin of many biological activities such as for example locomotion or digestion. These systems are generally modelled as recurrent neural networks whose parameters are tuned so that the network oscillates in a suitable way, this tuning being a non trivial task. It also appears that the link with the physical body that these oscillatory entities control has a fundamental importance, and it seems that most bodies used for experimental validation in the literature (walking robots, lamprey model, etc.) might be too complex to study. In this paper, we use a comparatively simple mechanical system, the nonholonomic vehicle referred to as the Roller-Racer, as a means towards testing different learning strategies for an Recurrent Neural Network-based (RNN) controller/guidance system. After a brief description of the Roller-Racer, we present as a preliminary study an RNN-based feed-forward controller whose parameters are obtained through the well-known teacher forcing learning algorithm, extended to learn signals with a continuous component.

AB - Central Pattern Generators (CPG) are oscillatory systems that are responsible for generating rhythmic patterns at the origin of many biological activities such as for example locomotion or digestion. These systems are generally modelled as recurrent neural networks whose parameters are tuned so that the network oscillates in a suitable way, this tuning being a non trivial task. It also appears that the link with the physical body that these oscillatory entities control has a fundamental importance, and it seems that most bodies used for experimental validation in the literature (walking robots, lamprey model, etc.) might be too complex to study. In this paper, we use a comparatively simple mechanical system, the nonholonomic vehicle referred to as the Roller-Racer, as a means towards testing different learning strategies for an Recurrent Neural Network-based (RNN) controller/guidance system. After a brief description of the Roller-Racer, we present as a preliminary study an RNN-based feed-forward controller whose parameters are obtained through the well-known teacher forcing learning algorithm, extended to learn signals with a continuous component.

M3 - Paper

ER -

Jouffroy G, Jouffroy J. A simple mechanical system for studying adaptive oscillatory neural networks. 2006. Afhandling præsenteret på IEEE Int. Conference on Systems, Man, and Cybernetics (SMC'06), Taipei, Taiwan.