Internet Archive Scholar
Filters
























54,314 Hits in 8.3 sec

Input-to-State Representation in linear reservoirs dynamics [article]

Pietro Verzelli and Cesare Alippi and Lorenzo Livi and Peter Tino
<span title="2021-02-12">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>

Preserved Fulltext

Web Archive Capture PDF (1.3 MB)
https://web.archive.org/web/20200326105649/https://arxiv.org/pdf/2003.10585v1.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit <a rel="external noopener" href="https://arxiv.org/pdf/2003.10585v1.pdf">the original URL</a>. The file type is <code>application/pdf</code>.

Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:

<span title="2020-03-24">2020</span> <span class="release-stage" >pre-print</span> <span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2003.10585v1">arXiv:2003.10585v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/2pzusgkl2baj5emkhq6jfmewoy">fatcat:2pzusgkl2baj5emkhq6jfmewoy</a> </span>

Other Versions

<span title="2021-01-05">2021</span> <span class="release-stage" >pre-print</span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2003.10585v2">arXiv:2003.10585v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/acx5wihg7rdhraxpafuru5v2ou">fatcat:acx5wihg7rdhraxpafuru5v2ou</a> </span>
Such a matrix encodes salient characteristics of the network dynamics; in particular, its rank represents an input-indepedent measure of the memory capacity of the network.  ...  Reservoir computing is a popular approach to design recurrent neural networks, due to its training simplicity and approximation performance.  ...  Introduction Despite of being applied to a large variety of tasks, Recurrent Neural Networks (RNNs) are far from being fully understood and perfomance improvements are usually driven by heuristics.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2003.10585v3">arXiv:2003.10585v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/qeucvlukb5epdlmemwihro3oqa">fatcat:qeucvlukb5epdlmemwihro3oqa</a> </span>
<span class="ui label basic blue small">Multiple Versions</span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200326105649/https://arxiv.org/pdf/2003.10585v1.pdf" title="fulltext PDF download [not primary version]" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <span style="color: #f43e3e;">&#10033;</span> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2003.10585v3" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>
Citation

Pietro Verzelli and Cesare Alippi and Lorenzo Livi and Peter Tino. "Input-to-State Representation in linear reservoirs dynamics." arXiv (2021)

Internal representation dynamics and geometry in recurrent neural networks [article]

Stefan Horoi, Guillaume Lajoie, Guy Wolf
<span title="2020-01-14">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>

Preserved Fulltext

Web Archive Capture PDF (235.3 kB)
https://web.archive.org/web/20200321010525/https://arxiv.org/pdf/2001.03255v2.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit <a rel="external noopener" href="https://arxiv.org/pdf/2001.03255v2.pdf">the original URL</a>. The file type is <code>application/pdf</code>.

Other Versions

<span title="2020-01-09">2020</span> <span class="release-stage" >pre-print</span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2001.03255v1">arXiv:2001.03255v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/dqssxzqhwbhzfhxgckrskeuqsu">fatcat:dqssxzqhwbhzfhxgckrskeuqsu</a> </span>
The efficiency of recurrent neural networks (RNNs) in dealing with sequential data has long been established.  ...  Our work seeks to shed light onto how a vanilla RNN implements a simple classification task by analysing the dynamics of the network and the geometric properties of its hidden states.  ...  ., 2019) and (Fusi et al., 2016) seems to be maintained for recurrent neural networks.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2001.03255v2">arXiv:2001.03255v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/6uudtlnwnrhdfht725dyy7go4m">fatcat:6uudtlnwnrhdfht725dyy7go4m</a> </span>
<span class="ui label basic blue small">Multiple Versions</span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200321010525/https://arxiv.org/pdf/2001.03255v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2001.03255v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>
Citation

Stefan Horoi, Guillaume Lajoie, Guy Wolf. "Internal representation dynamics and geometry in recurrent neural networks." arXiv (2020)

Spatiotemporal Computations of an Excitable and Plastic Brain: Neuronal Plasticity Leads to Noise-Robust and Noise-Constructive Computations

Hazem Toutounji, Gordon Pipa, Olaf Sporns
<span title="2014-03-20">2014</span> <i title="Public Library of Science (PLoS)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/ch57atmlprauhhbqdf7x4ytejm" style="color: black;">PLoS Computational Biology</a> </i> &nbsp;

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (2.0 MB)
https://web.archive.org/web/20171015142338/http://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.1003512&type=printable

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit <a rel="external noopener" href="http://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.1003512&type=printable">the original URL</a>. The file type is <code>application/pdf</code>.

To that end, we rigorously formulate the problem of neural representations as a relation in space between stimulus-induced neural activity and the asymptotic dynamics of excitable cortical networks.  ...  Nevertheless, no unifying account exists of how neurons in a recurrent cortical network learn to compute on temporally and spatially extended stimuli.  ...  recurrent neural network?  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1371/journal.pcbi.1003512">doi:10.1371/journal.pcbi.1003512</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/24651447">pmid:24651447</a> <a target="_blank" rel="external noopener" href="https://pubmed.ncbi.nlm.nih.gov/PMC3961183/">pmcid:PMC3961183</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/6dft4ndyifeqvpcy73qnpxzxoi">fatcat:6dft4ndyifeqvpcy73qnpxzxoi</a> </span>
<span class="ui label basic orange small" title="Directory of Open Access Journals">DOAJ</span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20171015142338/http://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.1003512&amp;type=printable" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/51/a2/51a2ee0b6d373daf4f1de60d940c3a0d2612f69d.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1371/journal.pcbi.1003512"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> plos.org </button> </a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3961183" title="pubmed link"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> pubmed.gov </button> </a>
Citation

Hazem Toutounji, Gordon Pipa, Olaf Sporns. "Spatiotemporal Computations of an Excitable and Plastic Brain: Neuronal Plasticity Leads to Noise-Robust and Noise-Constructive Computations." PLoS Computational Biology 10.3 (2014) e1003512

Deep neural networks: a new framework for modelling biological vision and brain information processing [article]

Nikolaus Kriegeskorte
<span title="2015-10-26">2015</span> <i title="Cold Spring Harbor Laboratory"> bioRxiv </i> &nbsp; <span class="release-stage" >pre-print</span>

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (698.7 kB)
https://web.archive.org/web/20190503153604/https://www.biorxiv.org/content/biorxiv/early/2015/10/26/029876.full.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit <a rel="external noopener" href="https://www.biorxiv.org/content/biorxiv/early/2015/10/26/029876.full.pdf">the original URL</a>. The file type is <code>application/pdf</code>.

Recent advances in neural network modelling have enabled major strides in computer vision and other artificial intelligence applications.  ...  Artificial neural networks are inspired by the brain and their computations could be implemented in biological neurons.  ...  Building recurrent neural network models whose representational dynamics resemble those of biological brains. 7.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1101/029876">doi:10.1101/029876</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/lxuwpdhzrvhpdmtyzg33ogwncy">fatcat:lxuwpdhzrvhpdmtyzg33ogwncy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190503153604/https://www.biorxiv.org/content/biorxiv/early/2015/10/26/029876.full.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/04/d5/04d539af1874e4e63ee55fe12ae6aeaf77391354.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1101/029876"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> biorxiv.org </button> </a>
Citation

Nikolaus Kriegeskorte. "Deep neural networks: a new framework for modelling biological vision and brain information processing." bioRxiv (2015)

Improving the State Space Organization of Untrained Recurrent Networks [chapter]

Michal Čerňanský, Matej Makula, Ľubica Beňušková
<span title="">2009</span> <i title="Springer Berlin Heidelberg"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/2w3awgokqne6te4nvlofavy5a4" style="color: black;">Lecture Notes in Computer Science</a> </i> &nbsp;

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (160.7 kB)
https://web.archive.org/web/20110725032547/http://www2.fiit.stuba.sk:80/~cernans/main/publications/iconip2008_paper_cernansky_b.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2011; you can also visit <a rel="external noopener" href="http://www2.fiit.stuba.sk:80/~cernans/main/publications/iconip2008_paper_cernansky_b.pdf">the original URL</a>. The file type is <code>application/pdf</code>.

In this work we demonstrate that the state space organization of untrained recurrent neural network can be significantly improved by choosing appropriate input representations.  ...  Recurrent neural networks are frequently used in cognitive science community for modeling linguistic structures.  ...  Here we studied performance of models using contractive dynamics of untrained recurrent networks with inputs representations extracted from word co-occurrence statistics as described in [13] .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-642-02490-0_82">doi:10.1007/978-3-642-02490-0_82</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/oaw7c2uez5h7dm7a37642uczju">fatcat:oaw7c2uez5h7dm7a37642uczju</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20110725032547/http://www2.fiit.stuba.sk:80/~cernans/main/publications/iconip2008_paper_cernansky_b.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/ad/25/ad25150112ccca83aef3c6ce1dfba09f0f41d0a3.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-642-02490-0_82"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>
Citation

Michal Čerňanský, Matej Makula, Ľubica Beňušková. "Improving the State Space Organization of Untrained Recurrent Networks." Lecture Notes in Computer Science (2009) 671-678

Localist Attractor Networks

Richard S. Zemel, Michael C. Mozer
<span title="">2001</span> <i title="MIT Press - Journals"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/rckx6fqoszfvva5c53bqivu5am" style="color: black;">Neural Computation</a> </i> &nbsp;

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (160.5 kB)
https://web.archive.org/web/20170830030534/http://www.cs.colorado.edu/~mozer/Research/Selected%20Publications/reprints/Mozer2008.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit <a rel="external noopener" href="http://www.cs.colorado.edu/~mozer/Research/Selected%20Publications/reprints/Mozer2008.pdf">the original URL</a>. The file type is <code>application/pdf</code>.

Artificial neural networks (ANNs), sometimes referred to as connectionist networks, are computational models based loosely on the neural architecture of the brain.  ...  A particular type of ANN, called an attractor network, is central to computational theories of consciousness, because attractor networks can be analyzed in terms of properties-such as temporal stability  ...  Attractor dynamics are achieved by many neural network architectures, including Hopfield networks, Harmony networks, Boltzmann Machines, adaptive resonance networks, and recurrent back propagation networks  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1162/08997660151134325">doi:10.1162/08997660151134325</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/11359644">pmid:11359644</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/saxckfc6p5gq5ndzdtg2ch5d4m">fatcat:saxckfc6p5gq5ndzdtg2ch5d4m</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170830030534/http://www.cs.colorado.edu/~mozer/Research/Selected%20Publications/reprints/Mozer2008.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/87/7e/877e930454383db03c80b33a5951f0e2cb5b3225.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1162/08997660151134325"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> mitpressjournals.org </button> </a>
Citation

Richard S. Zemel, Michael C. Mozer. "Localist Attractor Networks." Neural Computation 13.5 (2001) 1045-1064

Fuzzy finite-state automata can be deterministically encoded into recurrent neural networks

C.W. Omlin, K.K. Thornber, C.L. Giles
<span title="">1998</span> <i title="Institute of Electrical and Electronics Engineers (IEEE)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/7dwepyc5xbc47narcaqganu4vu" style="color: black;">IEEE transactions on fuzzy systems</a> </i> &nbsp;

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (475.3 kB)
https://web.archive.org/web/20190305130939/http://pdfs.semanticscholar.org/d321/cd2ac3330ef870811f73a0a35a472a4835c6.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit <a rel="external noopener" href="http://pdfs.semanticscholar.org/d321/cd2ac3330ef870811f73a0a35a472a4835c6.pdf">the original URL</a>. The file type is <code>application/pdf</code>.

Based on previous work on encoding DFAs in discrete-time, secondorder recurrent neural networks, we propose an algorithm that constructs an augmented recurrent neural network that encodes a FFA and recognizes  ...  There has been an increased interest in combining fuzzy systems with neural networks because fuzzy neural systems merge the advantages of both paradigms.  ...  Based on a previous result on encoding stable representations of nite-state dynamics in recurrent networks, we have shown how FFAs can be encoded in recurrent networks that compute string membership functions  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/91.660809">doi:10.1109/91.660809</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/bpv6mri2dfca7aljqmbpfrxq5y">fatcat:bpv6mri2dfca7aljqmbpfrxq5y</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190305130939/http://pdfs.semanticscholar.org/d321/cd2ac3330ef870811f73a0a35a472a4835c6.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/d3/21/d321cd2ac3330ef870811f73a0a35a472a4835c6.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/91.660809"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>
Citation

C.W. Omlin, K.K. Thornber, C.L. Giles. "Fuzzy finite-state automata can be deterministically encoded into recurrent neural networks." IEEE transactions on fuzzy systems 6.1 (1998) 76-89

Approaches Based on Markovian Architectural Bias in Recurrent Neural Networks [chapter]

Matej Makula, Michal Čerňanský, Ľubica Beňušková
<span title="">2004</span> <i title="Springer Berlin Heidelberg"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/2w3awgokqne6te4nvlofavy5a4" style="color: black;">Lecture Notes in Computer Science</a> </i> &nbsp;

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (114.1 kB)
https://web.archive.org/web/20110725032613/http://www2.fiit.stuba.sk:80/~cernans/main/publications/sofsem2004_paper_makula.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2011; you can also visit <a rel="external noopener" href="http://www2.fiit.stuba.sk:80/~cernans/main/publications/sofsem2004_paper_makula.pdf">the original URL</a>. The file type is <code>application/pdf</code>.

Recent studies show that state-space dynamics of randomly initialized recurrent neural network (RNN) has interesting and potentially useful properties even without training.  ...  More precisely, when initializing RNN with small weights, recurrent unit activities reflect history of inputs presented to the network according to the Markovian scheme.  ...  Introduction The key part of recurrent neural networks (RNNs) performance is encoded in activities of recurrent units (network state) and their variations in time (network dynamics).  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-540-24618-3_22">doi:10.1007/978-3-540-24618-3_22</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/vm5ogwcvuzczfpfswior6tmm7u">fatcat:vm5ogwcvuzczfpfswior6tmm7u</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20110725032613/http://www2.fiit.stuba.sk:80/~cernans/main/publications/sofsem2004_paper_makula.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/2d/36/2d363fc3a5722d98cb2e2736c83c6af3dad2b527.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-540-24618-3_22"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>
Citation

Matej Makula, Michal Čerňanský, Ľubica Beňušková. "Approaches Based on Markovian Architectural Bias in Recurrent Neural Networks." Lecture Notes in Computer Science (2004) 257-264

Equivalence in knowledge representation: automata, recurrent neural networks, and dynamical fuzzy systems

C.L. Giles, C.W. Omlin, K.K. Thornber
<span title="">1999</span> <i title="Institute of Electrical and Electronics Engineers (IEEE)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/yfvtieuumfamvmjlc255uckdlm" style="color: black;">Proceedings of the IEEE</a> </i> &nbsp;

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (594.4 kB)
https://web.archive.org/web/20060104212429/http://clgiles.ist.psu.edu:80/papers/Proc-IEEE-1999-knowledge-rep.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2006; you can also visit <a rel="external noopener" href="http://clgiles.ist.psu.edu:80/papers/Proc-IEEE-1999-knowledge-rep.pdf">the original URL</a>. The file type is <code>application/pdf</code>.

We also prove the stability of fuzzy finite state dynamics of the constructed neural networks for finite values of network weight and, through simulations, give empirical validation of the proofs.  ...  neural network.  ...  in a recurrent neural network.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/5.784244">doi:10.1109/5.784244</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ksy7ysm4inbk5mamvopdgsguse">fatcat:ksy7ysm4inbk5mamvopdgsguse</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20060104212429/http://clgiles.ist.psu.edu:80/papers/Proc-IEEE-1999-knowledge-rep.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/7d/ea/7dea7cbbbab5d81c08ccf6680838bc4543ff6402.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/5.784244"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>
Citation

C.L. Giles, C.W. Omlin, K.K. Thornber. "Equivalence in knowledge representation: automata, recurrent neural networks, and dynamical fuzzy systems." Proceedings of the IEEE 87.9 (1999) 1623-1640

AB009. Learning dynamics in a neural network model of the primary visual cortex

Hugo Ladret, Laurent Perrinet
<span title="">2019</span> <i title="AME Publishing Company"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/fmsrzkq5trc3de6ncuwhhdgfxu" style="color: black;">Annals of Eye Science</a> </i> &nbsp;

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (69.8 kB)
https://web.archive.org/web/20200709214542/http://aes.amegroups.com/article/download/5214/pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit <a rel="external noopener" href="http://aes.amegroups.com/article/download/5214/pdf">the original URL</a>. The file type is <code>application/pdf</code>.

Here, we present a recurrent spiking neural network that is capable of spike timing dependent plasticity (STDP) and we demonstrate its capacity to discriminate spatio-temporal orientation patterns in noisy  ...  biorealism in the context of learning visual inputs.  ...  Learning dynamics in a neural network model of the primary visual cortex. Ann Eye Sci 2019;4:AB009.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.21037/aes.2019.ab009">doi:10.21037/aes.2019.ab009</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/j7zxq2odzna3xmieyufruqggqq">fatcat:j7zxq2odzna3xmieyufruqggqq</a> </span>
<span class="ui label basic orange small" title="Open Access">Open Access</span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200709214542/http://aes.amegroups.com/article/download/5214/pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/3c/69/3c69c771eb78fb9a7afb8fa8f5f00cb4321f3865.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.21037/aes.2019.ab009"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> Publisher / doi.org </button> </a>
Citation

Hugo Ladret, Laurent Perrinet. "AB009. Learning dynamics in a neural network model of the primary visual cortex." Annals of Eye Science (2019) AB009-AB009

Dynamic updating of distributed neural representations using forward models

Eric L. Sauser, Aude G. Billard
<span title="">2006</span> <i title="Springer Nature"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/yygdrbxuwbhipmoa6ihwvrwwue" style="color: black;">Biological cybernetics</a> </i> &nbsp;

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (869.4 kB)
https://web.archive.org/web/20170818101352/https://infoscience.epfl.ch/record/113928/files/SB_BiolCyber_2006.pdf?version=1

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit <a rel="external noopener" href="https://infoscience.epfl.ch/record/113928/files/SB_BiolCyber_2006.pdf?version=1">the original URL</a>. The file type is <code>application/pdf</code>.

Indeed, we show that a relatively simple extension of the classical neural field models can endow these networks with additional dynamic properties for updating their internal representation using external  ...  In this paper, we present a continuous attractor network model that we hypothesize will give some suggestion of the mechanisms underlying several neural processes such as velocity tuning to visual stimulus  ...  Schöner for a helpful discussion concerning the problem of response latency occurring in recurrent models of sensorimotor transformations.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/s00422-006-0131-3">doi:10.1007/s00422-006-0131-3</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/17143650">pmid:17143650</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/7reudjdts5a2xevjnmuged55oq">fatcat:7reudjdts5a2xevjnmuged55oq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170818101352/https://infoscience.epfl.ch/record/113928/files/SB_BiolCyber_2006.pdf?version=1" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/6c/da/6cdabc2b8821407148d8568bea627bdea075459c.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/s00422-006-0131-3"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>
Citation

Eric L. Sauser, Aude G. Billard. "Dynamic updating of distributed neural representations using forward models." Biological cybernetics 95.6 (2006) 567-588

Equivalence in Knowledge Representation [chapter]

C Lee Giles, Christian Omlin, K Thornber
<span title="1999-12-20">1999</span> <i title="CRC Press"> International Series on Computational Intelligence </i> &nbsp;

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (594.4 kB)
https://web.archive.org/web/20060104212429/http://clgiles.ist.psu.edu:80/papers/Proc-IEEE-1999-knowledge-rep.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2006; you can also visit <a rel="external noopener" href="http://clgiles.ist.psu.edu:80/papers/Proc-IEEE-1999-knowledge-rep.pdf">the original URL</a>. The file type is <code>application/pdf</code>.

We also prove the stability of fuzzy finite state dynamics of the constructed neural networks for finite values of network weight and, through simulations, give empirical validation of the proofs.  ...  neural network.  ...  in a recurrent neural network.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1201/9781420049176.ch5">doi:10.1201/9781420049176.ch5</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/3pcc3ptpw5dadgt7akqmiaxncy">fatcat:3pcc3ptpw5dadgt7akqmiaxncy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20060104212429/http://clgiles.ist.psu.edu:80/papers/Proc-IEEE-1999-knowledge-rep.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/7d/ea/7dea7cbbbab5d81c08ccf6680838bc4543ff6402.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1201/9781420049176.ch5"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>
Citation

C Lee Giles, Christian Omlin, K Thornber. "Equivalence in Knowledge Representation." International Series on Computational Intelligence (1999)

CYK Parsing over Distributed Representations

Fabio Massimo Zanzotto, Giorgio Satta, Giordano Cristini
<span title="2020-10-15">2020</span> <i title="MDPI AG"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/63zsvf7vxzfznojpqgfvpyk2lu" style="color: black;">Algorithms</a> </i> &nbsp;

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (383.3 kB)
https://web.archive.org/web/20201017012232/https://res.mdpi.com/d_attachment/algorithms/algorithms-13-00262/article_deploy/algorithms-13-00262.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit <a rel="external noopener" href="https://res.mdpi.com/d_attachment/algorithms/algorithms-13-00262/article_deploy/algorithms-13-00262.pdf">the original URL</a>. The file type is <code>application/pdf</code>.

D-CYK uses matrix multiplication on real number matrices of a size independent of the length of the input string. These operations are compatible with recurrent neural networks.  ...  By showing that CYK can be entirely performed on distributed representations, we open the way to the definition of recurrent layer neural networks that can process general context-free languages.  ...  The parser employs a recurrent neural network to compute a distributed representation for the parsing history based on unlimited portions of the stack and the input queue. Dyer et al.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/a13100262">doi:10.3390/a13100262</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/wcovlq4ayjg3nfo4j6fud7eer4">fatcat:wcovlq4ayjg3nfo4j6fud7eer4</a> </span>
<span class="ui label basic orange small" title="Directory of Open Access Journals">DOAJ</span> <span class="ui label basic orange small" title="Szcezepanski OA Journal List">Szczepanski</span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201017012232/https://res.mdpi.com/d_attachment/algorithms/algorithms-13-00262/article_deploy/algorithms-13-00262.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/2e/4a/2e4a08df01ee04fa63b6bdac4ab7c6cb8e8cb0be.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/a13100262"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> mdpi.com </button> </a>
Citation

Fabio Massimo Zanzotto, Giorgio Satta, Giordano Cristini. "CYK Parsing over Distributed Representations." Algorithms 13.10 (2020) 262

The brain as an efficient and robust adaptive learner [article]

Sophie Denève, Alireza Alemi, Ralph Bourdoukan
<span title="2017-05-22">2017</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (2.9 MB)
https://web.archive.org/web/20200929163321/https://arxiv.org/ftp/arxiv/papers/1705/1705.08031.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit <a rel="external noopener" href="https://arxiv.org/ftp/arxiv/papers/1705/1705.08031.pdf">the original URL</a>. The file type is <code>application/pdf</code>.

Most sensory and motor tasks can be described as dynamical systems and could presumably be learned by adjusting connection weights in a recurrent biological neural network.  ...  However, this is greatly complicated by the credit assignment problem for learning in recurrent network, e.g. the contribution of each connection to the global output error cannot be determined based only  ...  In effect, the recurrent connections remove all redundancies between neural spike trains due to their shared input.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1705.08031v1">arXiv:1705.08031v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ibhfp32exbbitnw3befgehmx34">fatcat:ibhfp32exbbitnw3befgehmx34</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200929163321/https://arxiv.org/ftp/arxiv/papers/1705/1705.08031.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/f2/46/f24696bf23cade6c40afc6d20cb3fb35978fb8a4.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1705.08031v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>
Citation

Sophie Denève, Alireza Alemi, Ralph Bourdoukan. "The brain as an efficient and robust adaptive learner." arXiv (2017)

DRAGNN: A Transition-based Framework for Dynamically Connected Neural Networks [article]

Lingpeng Kong, Chris Alberti, Daniel Andor, Ivan Bogatyy, David Weiss
<span title="2017-03-13">2017</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (793.0 kB)
https://web.archive.org/web/20191013120123/https://arxiv.org/pdf/1703.04474v1.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit <a rel="external noopener" href="https://arxiv.org/pdf/1703.04474v1.pdf">the original URL</a>. The file type is <code>application/pdf</code>.

We call our approach Dynamic Recurrent Acyclic Graphical Neural Networks, or DRAGNN.  ...  In addition to hidden layer activations, TBRUs have discrete state dynamics that allow network connections to be built dynamically as a function of intermediate activations.  ...  We therefore call our approach Dynamic Recurrent Acyclic Graphical Neural Networks, or DRAGNN. DRAGNN has several distinct modeling advantages over traditional fixed neural architectures.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1703.04474v1">arXiv:1703.04474v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/z4ox74korjftrk6azprszqivty">fatcat:z4ox74korjftrk6azprszqivty</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20191013120123/https://arxiv.org/pdf/1703.04474v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/6d/67/6d671e0e26d239bd6a0b8f67d5fc49a76d733f29.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1703.04474v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>
Citation

Lingpeng Kong, Chris Alberti, Daniel Andor, Ivan Bogatyy, David Weiss. "DRAGNN: A Transition-based Framework for Dynamically Connected Neural Networks." arXiv (2017)

&laquo; Previous Showing results 1 &mdash; 15 out of 54,314 results