 |
| Research article summary (published 29 Jun 2002): |
Self-selected modular recurrent neural networks with postural and inertial subnetworks applied to complex movements.
Full Abstract
It has been shown that dynamic recurrent neural networks are successful in identifying the complex mapping relationship between full-wave-rectified electromyographic (EMG) signals and limb trajectories during complex movements. These connectionist models include two types of adaptive parameters:
the interconnection weights between the units and the time constants associated to each neuron-like unit; they are governed by continuous-time equations. Due to their internal structure, these models are particularly appropriate to solve dynamical tasks (with time-varying input and output signals). We show in this paper that the introduction of a modular organization dedicated to different aspects of the dynamical mapping including privileged communication channels can refine the architecture of these recurrent networks. We first divide the initial individual network into two communicating subnetworks. These two modules receive the same EMG signals as input but are involved in different identification tasks related to position and acceleration. We then show that the introduction of an artificial distance in the model (using a Gaussian modulation factor of weights) induces a reduced modular architecture based on a self-elimination of null synaptic weights. Moreover, this self-selected reduced model based on two subnetworks performs the identification task better than the original single network while using fewer free parameters (better learning curve and better identification quality). We also show that this modular network exhibits several features that can be considered as biologically plausible after the learning process:
self-selection of a specific inhibitory communicating path between both subnetworks after the learning process, appearance of tonic and phasic neurons, and coherent distribution of the values of the time constants within each subnetwork.
Learn Faster Today Improve your study skills
Author information
Author/s: Draye, Jean-Philippe (JP); Winters, Jack M (JM); Cheron, Guy (G);
Affiliation: Avaya Belgium sa/nv, Waterloo Office Park, Building K, Drève Richelle 161, 1410 Waterloo, Belgium. jdraye@avaya.com
Journal and publication information
Publication Type: Journal Article
Journal: Biological cybernetics (Biol Cybern), published in Germany. (Language: eng)
Reference: 2002-Jul; vol 87 (issue 1) : pp 27-39
Dates: Created 2002/07/11; Completed 2002/12/31; Revised 2004/11/17;
PMID: 12111266, status: MEDLINE (last retrieval date: 11/6/2008)
Sourced from the National Library of Medicine. Abstract text and other information may be subject to copyright.
External Links for this article (including full text providers, if available):
Click Electronic Full-text Provider Links to see options for finding the electronic full text links to this article. Note there may be a subscription or fee required for access to the full text. See our FAQ for information on finding FREE full text articles.
This article may also be located in paper journal collections available in many libraries. Use the Journal and Publication Information above to find the full article.
MeSH headings (categories)
This article was linked to the MESH Headings shown below.
|
Related articles
This article has not been indexed for related articles as yet, however you can still use the live related article search links below.
See a large map of 100+ related articles.