Neuromodulation Mechanisms for the Cooperation of Artificial Neural Networks
Identifieur interne : 00C453 ( Main/Curation ); précédent : 00C452; suivant : 00C454Neuromodulation Mechanisms for the Cooperation of Artificial Neural Networks
Auteurs : L. Beaugé ; F. AlexandreSource :
English descriptors
Abstract
Learning and memory are still too rigid in neural networks compared to human characteristics. These artificial networks remain monolithic and not very flexible. Biological data show that the cortex is a set of subsystems which dynamically interact. Moreover, neurobiology has brought to the fore the importance of neuromodulation in these interactions. To realize dynamic cooperating systems, we have concentrated our efforts at several scales\, ; from a microscopic scale where modulatory synapses and complex cell functioning have been studied, towards a macroscopic scale where cooperating systems have been tackled according to an example relative to visual pattern recognition. In this paper, we present at first the microscopic level by introducing some modulation principles. Two platforms allow us to experiment with synaptic modulation rules, and their results show specific characteristic for two kinds of modulation principles. To illustrate their roles in cooperation mechanisms (sensitization or context contribution), at a macroscopic level, we describe a model applied to pattern recognition inspired by parieto-temporal interactions of the brain.
Links toward previous steps (curation, corpus...)
- to stream Crin, to step Corpus: Pour aller vers cette notice dans l'étape Curation :001955
- to stream Crin, to step Curation: Pour aller vers cette notice dans l'étape Curation :001955
- to stream Crin, to step Checkpoint: Pour aller vers cette notice dans l'étape Curation :002C65
- to stream Main, to step Merge: Pour aller vers cette notice dans l'étape Curation :00CD10
Links to Exploration step
CRIN:beauge95aLe document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" wicri:score="280">Neuromodulation Mechanisms for the Cooperation of Artificial Neural Networks</title>
</titleStmt>
<publicationStmt><idno type="RBID">CRIN:beauge95a</idno>
<date when="1995" year="1995">1995</date>
<idno type="wicri:Area/Crin/Corpus">001955</idno>
<idno type="wicri:Area/Crin/Curation">001955</idno>
<idno type="wicri:explorRef" wicri:stream="Crin" wicri:step="Curation">001955</idno>
<idno type="wicri:Area/Crin/Checkpoint">002C65</idno>
<idno type="wicri:explorRef" wicri:stream="Crin" wicri:step="Checkpoint">002C65</idno>
<idno type="wicri:Area/Main/Merge">00CD10</idno>
<idno type="wicri:Area/Main/Curation">00C453</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title xml:lang="en">Neuromodulation Mechanisms for the Cooperation of Artificial Neural Networks</title>
<author><name sortKey="Beauge, L" sort="Beauge, L" uniqKey="Beauge L" first="L." last="Beaugé">L. Beaugé</name>
</author>
<author><name sortKey="Alexandre, F" sort="Alexandre, F" uniqKey="Alexandre F" first="F." last="Alexandre">F. Alexandre</name>
</author>
</analytic>
</biblStruct>
</sourceDesc>
</fileDesc>
<profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>cortical column</term>
<term>learning and memory</term>
<term>modulation</term>
<term>neural network</term>
<term>sigma-pi unit</term>
</keywords>
</textClass>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en" wicri:score="4448">Learning and memory are still too rigid in neural networks compared to human characteristics. These artificial networks remain monolithic and not very flexible. Biological data show that the cortex is a set of subsystems which dynamically interact. Moreover, neurobiology has brought to the fore the importance of neuromodulation in these interactions. To realize dynamic cooperating systems, we have concentrated our efforts at several scales\, ; from a microscopic scale where modulatory synapses and complex cell functioning have been studied, towards a macroscopic scale where cooperating systems have been tackled according to an example relative to visual pattern recognition. In this paper, we present at first the microscopic level by introducing some modulation principles. Two platforms allow us to experiment with synaptic modulation rules, and their results show specific characteristic for two kinds of modulation principles. To illustrate their roles in cooperation mechanisms (sensitization or context contribution), at a macroscopic level, we describe a model applied to pattern recognition inspired by parieto-temporal interactions of the brain.</div>
</front>
</TEI>
</record>
Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Wicri/Lorraine/explor/InforLorV4/Data/Main/Curation
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 00C453 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Curation/biblio.hfd -nk 00C453 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien |wiki= Wicri/Lorraine |area= InforLorV4 |flux= Main |étape= Curation |type= RBID |clé= CRIN:beauge95a |texte= Neuromodulation Mechanisms for the Cooperation of Artificial Neural Networks }}
![]() | This area was generated with Dilib version V0.6.33. | ![]() |