Ontology type: schema:Chapter Open Access: True
2017
AUTHORSAlex Pitti , Philippe Gaussier , Mathias Quoy
ABSTRACTHuman working memory is capable to generate dynamically robust and flexible neuronal sequences for action planning, problem solving and decision making. However, current neurocomputational models of working memory find hard to achieve these capabilities since intrinsic noise is difficult to stabilize over time and destroys global synchrony. As part of the principle of free-energy minimization proposed by Karl Friston, we propose a novel neural architecture to optimize the free-energy inherent to spiking recurrent neural networks to regulate their activity. We show for the first time that it is possible to stabilize iteratively the long-range control of a recurrent spiking neurons network over long sequences. We identify our architecture as the working memory composed by the Basal Ganglia and the Intra-Parietal Lobe for action selection and we make some comparisons with other networks such as deep neural networks and neural Turing machines. We name our architecture INFERNO for Iterative Free-Energy Optimization for Recurrent Neural Network. abstract environment. More... »
PAGES421-428
Advances in Neural Networks - ISNN 2017
ISBN
978-3-319-59071-4
978-3-319-59072-1
http://scigraph.springernature.com/pub.10.1007/978-3-319-59072-1_50
DOIhttp://dx.doi.org/10.1007/978-3-319-59072-1_50
DIMENSIONShttps://app.dimensions.ai/details/publication/pub.1086389855
JSON-LD is the canonical representation for SciGraph data.
TIP: You can open this SciGraph record using an external JSON-LD service: JSON-LD Playground Google SDTT
[
{
"@context": "https://springernature.github.io/scigraph/jsonld/sgcontext.json",
"about": [
{
"id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/0801",
"inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/",
"name": "Artificial Intelligence and Image Processing",
"type": "DefinedTerm"
},
{
"id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/08",
"inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/",
"name": "Information and Computing Sciences",
"type": "DefinedTerm"
}
],
"author": [
{
"affiliation": {
"name": [
"Laboratoire ETIS, CNRS UMR 8051, University of Cergy-Pontoise, ENSEA"
],
"type": "Organization"
},
"familyName": "Pitti",
"givenName": "Alex",
"type": "Person"
},
{
"affiliation": {
"name": [
"Laboratoire ETIS, CNRS UMR 8051, University of Cergy-Pontoise, ENSEA"
],
"type": "Organization"
},
"familyName": "Gaussier",
"givenName": "Philippe",
"id": "sg:person.01041272554.05",
"sameAs": [
"https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01041272554.05"
],
"type": "Person"
},
{
"affiliation": {
"name": [
"Laboratoire ETIS, CNRS UMR 8051, University of Cergy-Pontoise, ENSEA"
],
"type": "Organization"
},
"familyName": "Quoy",
"givenName": "Mathias",
"id": "sg:person.010556353111.37",
"sameAs": [
"https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010556353111.37"
],
"type": "Person"
}
],
"citation": [
{
"id": "https://doi.org/10.1146/annurev.neuro.051508.135546",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1005200190"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1152/jn.00026.2013",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1008062270"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1098/rstb.2005.1622",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1009065990"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1016/s0303-2647(98)00070-7",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1017445912"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1016/j.jphysparis.2006.10.001",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1026071571"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1016/j.tics.2011.05.007",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1026226705"
],
"type": "CreativeWork"
},
{
"id": "sg:pub.10.1038/srep22959",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1042705826",
"https://doi.org/10.1038/srep22959"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1016/j.conb.2015.11.004",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1043320675"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1016/j.neuron.2015.09.019",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1048787902"
],
"type": "CreativeWork"
},
{
"id": "sg:pub.10.1038/nature20101",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1050701470",
"https://doi.org/10.1038/nature20101"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1142/s021963520400049x",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1063002592"
],
"type": "CreativeWork"
},
{
"id": "https://app.dimensions.ai/details/publication/pub.1078846892",
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1371/journal.pone.0173684",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1084300468"
],
"type": "CreativeWork"
}
],
"datePublished": "2017",
"datePublishedReg": "2017-01-01",
"description": "Human working memory is capable to generate dynamically robust and flexible neuronal sequences for action planning, problem solving and decision making. However, current neurocomputational models of working memory find hard to achieve these capabilities since intrinsic noise is difficult to stabilize over time and destroys global synchrony. As part of the principle of free-energy minimization proposed by Karl Friston, we propose a novel neural architecture to optimize the free-energy inherent to spiking recurrent neural networks to regulate their activity. We show for the first time that it is possible to stabilize iteratively the long-range control of a recurrent spiking neurons network over long sequences. We identify our architecture as the working memory composed by the Basal Ganglia and the Intra-Parietal Lobe for action selection and we make some comparisons with other networks such as deep neural networks and neural Turing machines. We name our architecture INFERNO for Iterative Free-Energy Optimization for Recurrent Neural Network. abstract environment.",
"editor": [
{
"familyName": "Cong",
"givenName": "Fengyu",
"type": "Person"
},
{
"familyName": "Leung",
"givenName": "Andrew",
"type": "Person"
},
{
"familyName": "Wei",
"givenName": "Qinglai",
"type": "Person"
}
],
"genre": "chapter",
"id": "sg:pub.10.1007/978-3-319-59072-1_50",
"inLanguage": [
"en"
],
"isAccessibleForFree": true,
"isPartOf": {
"isbn": [
"978-3-319-59071-4",
"978-3-319-59072-1"
],
"name": "Advances in Neural Networks - ISNN 2017",
"type": "Book"
},
"name": "INFERNO: A Novel Architecture for Generating Long Neuronal Sequences with Spikes",
"pagination": "421-428",
"productId": [
{
"name": "doi",
"type": "PropertyValue",
"value": [
"10.1007/978-3-319-59072-1_50"
]
},
{
"name": "readcube_id",
"type": "PropertyValue",
"value": [
"44601a69163837288a3617a283619f6554636e8db73ea0c508df818e16913fbc"
]
},
{
"name": "dimensions_id",
"type": "PropertyValue",
"value": [
"pub.1086389855"
]
}
],
"publisher": {
"location": "Cham",
"name": "Springer International Publishing",
"type": "Organisation"
},
"sameAs": [
"https://doi.org/10.1007/978-3-319-59072-1_50",
"https://app.dimensions.ai/details/publication/pub.1086389855"
],
"sdDataset": "chapters",
"sdDatePublished": "2019-04-15T18:14",
"sdLicense": "https://scigraph.springernature.com/explorer/license/",
"sdPublisher": {
"name": "Springer Nature - SN SciGraph project",
"type": "Organization"
},
"sdSource": "s3://com-uberresearch-data-dimensions-target-20181106-alternative/cleanup/v134/2549eaecd7973599484d7c17b260dba0a4ecb94b/merge/v9/a6c9fde33151104705d4d7ff012ea9563521a3ce/jats-lookup/v90/0000000001_0000000264/records_8681_00000279.jsonl",
"type": "Chapter",
"url": "http://link.springer.com/10.1007/978-3-319-59072-1_50"
}
]Download the RDF metadata as: json-ld nt turtle xml License info
JSON-LD is a popular format for linked data which is fully compatible with JSON.
curl -H 'Accept: application/ld+json' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-59072-1_50'
N-Triples is a line-based linked data format ideal for batch operations.
curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-59072-1_50'
Turtle is a human-readable linked data format.
curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-59072-1_50'
RDF/XML is a standard XML format for linked data.
curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-59072-1_50'
This table displays all metadata directly associated to this object as RDF triples.
131 TRIPLES
23 PREDICATES
40 URIs
20 LITERALS
8 BLANK NODES