Filters








654 Hits in 5.3 sec

Gibbs Sampling with Low-Power Spiking Digital Neurons [article]

Srinjoy Das, Bruno Umbria Pedroni, Paul Merolla, John Arthur, Andrew S. Cassidy, Bryan L. Jackson, Dharmendra Modha, Gert Cauwenberghs, Ken Kreutz-Delgado
<span title="2015-03-27">2015</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
This paper demonstrates such an implementation on an array of digital spiking neurons with stochastic leak and threshold properties for inference tasks and presents some key performance metrics for such  ...  Inference and learning in these algorithms uses a Markov Chain Monte Carlo procedure called Gibbs sampling.  ...  Our proposed method of realization of the sigmoidal function with low-power, digital integrate-and-fire neurons is well suited for Gibbs sampling in RBMs and DBNs with parallel arrays of visible and hidden  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1503.07793v2">arXiv:1503.07793v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/cioz5qxolfgo5ew5vr5rypxvim">fatcat:cioz5qxolfgo5ew5vr5rypxvim</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200828094256/https://arxiv.org/pdf/1503.07793v2.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/1a/8b/1a8b28e8818a493f1f97d052ed543ecde1c79a39.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1503.07793v2" 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>

A Nonparametric Framework for Quantifying Generative Inference on Neuromorphic Systems [article]

Ojash Neopane, Srinjoy Das, Ery Arias-Castro, Kenneth Kreutz-Delgado
<span title="2016-02-18">2016</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Generative inference in such algorithms can be performed very efficiently on hardware using a Markov Chain Monte Carlo procedure called Gibbs sampling, where stochastic samples are drawn from noisy integrate  ...  and fire neurons implemented on neuromorphic substrates.  ...  on such substrates for ultra low-power, realtime applications.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1602.05996v1">arXiv:1602.05996v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/mf6up2zhrjapxdymbdrssmcgsq">fatcat:mf6up2zhrjapxdymbdrssmcgsq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200830065007/https://arxiv.org/pdf/1602.05996v1.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/b5/fc/b5fc298fcee9d789a9b67338a7f5d63a6b01695e.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1602.05996v1" 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>

Mapping Generative Models onto a Network of Digital Spiking Neurons

Bruno U. Pedroni, Srinjoy Das, John V. Arthur, Paul A. Merolla, Bryan L. Jackson, Dharmendra S. Modha, Kenneth Kreutz-Delgado, Gert Cauwenberghs
<span title="">2016</span> <i title="Institute of Electrical and Electronics Engineers (IEEE)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/l2dywgu6pbcsvgqv77yjgpr32e" style="color: black;">IEEE Transactions on Biomedical Circuits and Systems</a> </i> &nbsp;
For this, we first propose a method of producing the Gibbs sampler using bio-inspired digital noisy integrate-and-fire neurons.  ...  Next, we describe the process of mapping generative RBMs trained offline onto the IBM TrueNorth neurosynaptic processor -- a low-power digital neuromorphic VLSI substrate.  ...  THE TRUENORTH DIGITAL NEUROSYNAPTIC PROCESSOR IBM's TrueNorth is a very low-power, brain-inspired digital neurosynaptic processor [8] , with 4096 cores, totaling 1 million programmable spiking neurons  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/tbcas.2016.2539352">doi:10.1109/tbcas.2016.2539352</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/27214915">pmid:27214915</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/pfygt6j6tbc5rgpv2yuoyfgvbm">fatcat:pfygt6j6tbc5rgpv2yuoyfgvbm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200827190648/https://arxiv.org/vc/arxiv/papers/1509/1509.07302v1.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> <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/f2/b3/f2b3a872312f7249e9d251c68c5bfa90b1ce408b.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/tbcas.2016.2539352"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Event-driven contrastive divergence for spiking neuromorphic systems

Emre Neftci, Srinjoy Das, Bruno Pedroni, Kenneth Kreutz-Delgado, Gert Cauwenberghs
<span title="">2014</span> <i title="Frontiers Media SA"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/wrk3kouosrhcxiprcbguskdipu" style="color: black;">Frontiers in Neuroscience</a> </i> &nbsp;
Their implementation on neuromorphic hardware platforms emulating large-scale networks of spiking neurons can have significant advantages from the perspectives of scalability, power dissipation and real-time  ...  We demonstrate our approach by training an RBM composed of leaky I&F neurons with STDP synapses to learn a generative model of the MNIST hand-written digit dataset, and by testing it in recognition, generation  ...  drive the rest of the network without tending to induce spike-to-spike correlations (e.g., synchrony), which is incompatible with the assumptions made for sampling with I&F neurons and event-driven CD  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3389/fnins.2013.00272">doi:10.3389/fnins.2013.00272</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/24574952">pmid:24574952</a> <a target="_blank" rel="external noopener" href="https://pubmed.ncbi.nlm.nih.gov/PMC3922083/">pmcid:PMC3922083</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/erazltqd55ghffe2ge4db4ynny">fatcat:erazltqd55ghffe2ge4db4ynny</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190427053044/https://cloudfront.escholarship.org/dist/prd/content/qt30h9q6bf/qt30h9q6bf.pdf?t=olulzb" 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/4e/f4/4ef4ab1766614b8a605cb3308a07bc68ac3b03c4.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3389/fnins.2013.00272"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> frontiersin.org </button> </a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3922083" title="pubmed link"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> pubmed.gov </button> </a>

Spiking neurons with short-term synaptic plasticity form superior generative networks

Luziwei Leng, Roman Martel, Oliver Breitwieser, Ilja Bytschok, Walter Senn, Johannes Schemmel, Karlheinz Meier, Mihai A. Petrovici
<span title="2018-07-13">2018</span> <i title="Springer Nature"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/tnqhc2x2aneavcd3gx5h7mswhm" style="color: black;">Scientific Reports</a> </i> &nbsp;
We thereby uncover a powerful computational property of the biologically inspired, local, spike-triggered synaptic dynamics based simply on a limited pool of synaptic resources, which enables them to deal  ...  We demonstrate how similar results can be achieved in spiking networks endowed with local short-term synaptic plasticity.  ...  After training, we compared the generative output of a Gibbs sampler, an AST sampler and a spiking network with STP.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1038/s41598-018-28999-2">doi:10.1038/s41598-018-28999-2</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/30006554">pmid:30006554</a> <a target="_blank" rel="external noopener" href="https://pubmed.ncbi.nlm.nih.gov/PMC6045624/">pmcid:PMC6045624</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/kc6emgbx45ddtk4aeruonlaw64">fatcat:kc6emgbx45ddtk4aeruonlaw64</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190428033045/https://boris.unibe.ch/122402/1/Leng2018Nature_1.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/47/4b/474b1ea637a7b566fa8da3cb1117a848bc153722.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1038/s41598-018-28999-2"> <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> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6045624" title="pubmed link"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> pubmed.gov </button> </a>

Stochastic Synapses Enable Efficient Brain-Inspired Learning Machines

Emre O. Neftci, Bruno U. Pedroni, Siddharth Joshi, Maruan Al-Shedivat, Gert Cauwenberghs
<span title="2016-06-29">2016</span> <i title="Frontiers Media SA"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/wrk3kouosrhcxiprcbguskdipu" style="color: black;">Frontiers in Neuroscience</a> </i> &nbsp;
The spiking neuron-based synaptic sampling machines outperform existing spike-based unsupervised learners, while potentially offering substantial advantages in terms of power and complexity, and are thus  ...  Synaptic sampling machines perform equally well using discrete-timed artificial units (as in Hopfield networks) or continuous-timed leaky integrate & fire neurons.  ...  As in RBMs, the dSSM was sampled using Gibbs sampling. The continuous-time, spiking SSM consisted of a network of deterministic I&F spiking neurons, connected through stochastic (blank-out) synapses.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3389/fnins.2016.00241">doi:10.3389/fnins.2016.00241</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/27445650">pmid:27445650</a> <a target="_blank" rel="external noopener" href="https://pubmed.ncbi.nlm.nih.gov/PMC4925698/">pmcid:PMC4925698</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/x5jt5klkxfctbmjnlvyfmpel64">fatcat:x5jt5klkxfctbmjnlvyfmpel64</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20180725111304/https://cloudfront.escholarship.org/dist/prd/content/qt62t6f9rs/qt62t6f9rs.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/b2/06/b206d45bfacea3bdc962dd3c113b1c6b2e5961ba.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3389/fnins.2016.00241"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> frontiersin.org </button> </a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4925698" title="pubmed link"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> pubmed.gov </button> </a>

Dual stochasticity of neurons and synapses provides a biologically plausible learning [article]

Jun-nosuke Teramae
<span title="2019-10-21">2019</span> <i title="Cold Spring Harbor Laboratory"> bioRxiv </i> &nbsp; <span class="release-stage" >pre-print</span>
framework and provide an efficient and biologically-plausible learning algorithm that consistently explains various experimental findings of the brain, which includes statistics of cortical circuit and the power-low  ...  scaling of population activity of cortical neurons.  ...  circuit [31] , and response properties of cortical neurons including the nearly optimal power-low scaling of population activity [9] .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1101/811646">doi:10.1101/811646</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/n2hhlu6xpbhl7enumprmkuky6u">fatcat:n2hhlu6xpbhl7enumprmkuky6u</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200310101226/https://www.biorxiv.org/content/biorxiv/early/2019/10/24/811646.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/d9/56/d956113798eb82013f927e84e4c382a707208a97.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1101/811646"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> biorxiv.org </button> </a>

Building fast Bayesian computing machines out of intentionally stochastic, digital parts [article]

Vikash Mansinghka, Eric Jonas
<span title="2014-02-20">2014</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
compatible with the Poisson firing statistics of cortical neurons.  ...  We find that by connecting stochastic digital components according to simple mathematical rules, one can build massively parallel, low precision circuits that solve Bayesian inference problems and are  ...  acknowledge Tomaso Poggio, Thomas Knight, Gerald Sussman, Rakesh Kumar and Joshua Tenenbaum for numerous helpful discussions and comments on early drafts, and Tejas Kulkarni for contributions to the spiking  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1402.4914v1">arXiv:1402.4914v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/mnjmxywzyrgo5avrttcvsxosri">fatcat:mnjmxywzyrgo5avrttcvsxosri</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200908063642/https://arxiv.org/pdf/1402.4914v1.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/6c/b9/6cb94e0723660ce96a61b145701395d66edcc1b3.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1402.4914v1" 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>

Brain-Inspired Hardware Solutions for Inference in Bayesian Networks

Leila Bagheriye, Johan Kwisthout
<span title="2021-12-02">2021</span> <i title="Frontiers Media SA"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/wrk3kouosrhcxiprcbguskdipu" style="color: black;">Frontiers in Neuroscience</a> </i> &nbsp;
These efforts lead to several implementations ranging from digital circuits, mixed-signal circuits, to analog circuits by leveraging new emerging nonvolatile devices.  ...  Hence, developing probabilistic spiking neurons with low area and power consumption is highly required.  ...  SNNs are implemented on low-power event-driven hardware, and the time and energy consumption are proportional to the number of spike events.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3389/fnins.2021.728086">doi:10.3389/fnins.2021.728086</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/34924925">pmid:34924925</a> <a target="_blank" rel="external noopener" href="https://pubmed.ncbi.nlm.nih.gov/PMC8677599/">pmcid:PMC8677599</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/tihogzl6tfbpjdybwpggllwd5u">fatcat:tihogzl6tfbpjdybwpggllwd5u</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211206235738/https://fjfsdata01prod.blob.core.windows.net/articles/files/728086/pubmed-zip/.versions/1/.package-entries/fnins-15-728086/fnins-15-728086.pdf?sv=2018-03-28&amp;sr=b&amp;sig=0zL1Dpxp3xCQvJIgOfqumSME31QQzMJV8Dth9U9Uq3o%3D&amp;se=2021-12-06T23%3A58%3A05Z&amp;sp=r&amp;rscd=attachment%3B%20filename%2A%3DUTF-8%27%27fnins-15-728086.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/72/fe/72fe17f73ccdf9921c890f9a5cbd94336c1847e8.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3389/fnins.2021.728086"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> frontiersin.org </button> </a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8677599" title="pubmed link"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> pubmed.gov </button> </a>

Robustness of spiking Deep Belief Networks to noise and reduced bit precision of neuro-inspired hardware platforms

Evangelos Stromatias, Daniel Neil, Michael Pfeiffer, Francesco Galluppi, Steve B. Furber, Shih-Chii Liu
<span title="2015-07-09">2015</span> <i title="Frontiers Media SA"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/wrk3kouosrhcxiprcbguskdipu" style="color: black;">Frontiers in Neuroscience</a> </i> &nbsp;
The on-going work on design and construction of spike-based hardware platforms offers an alternative for running deep neural networks with significantly lower power consumption, but has to overcome hardware  ...  Furthermore, the network performance of spiking DBNs is characterized with regard to noise in the spiking input signal.  ...  Once trained, the single bit precision analog network can potentially be implemented on a digital neuron platform such as TrueNorth (Merolla et al., 2014b) , using the Gibbs sampling methods recently  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3389/fnins.2015.00222">doi:10.3389/fnins.2015.00222</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/26217169">pmid:26217169</a> <a target="_blank" rel="external noopener" href="https://pubmed.ncbi.nlm.nih.gov/PMC4496577/">pmcid:PMC4496577</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/f3bjob43irhg5owjbmpix5rmam">fatcat:f3bjob43irhg5owjbmpix5rmam</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190430003423/https://hal.sorbonne-universite.fr/hal-01266136/file/fnins-09-00222.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/1b/1c/1b1c93434fa537455d413a33d936922637cfc467.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3389/fnins.2015.00222"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> frontiersin.org </button> </a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4496577" title="pubmed link"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> pubmed.gov </button> </a>

Noise as a Resource for Computation and Learning in Networks of Spiking Neurons

Wolfgang Maass
<span title="">2014</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;
I will also describe why these results are paving the way for a qualitative jump in the computational capability and learning performance of neuromorphic networks of spiking neurons with noise, and for  ...  Recent theoretical results have provided insight into how this can be achieved: how noise enables networks of spiking neurons to carry out probabilistic inference through sampling and also enables creative  ...  Rueckert for scientific advice and help with the figures. He would also like to thank three anonymous reviewers for helpful suggestions.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/jproc.2014.2310593">doi:10.1109/jproc.2014.2310593</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/54mgt3scqje5flvjqnad45okfi">fatcat:54mgt3scqje5flvjqnad45okfi</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170829174432/http://www.igi.tugraz.at/psfiles/221.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/3d/43/3d43773f9dfc0c1630783367f00cb7065dc52671.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/jproc.2014.2310593"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Nyquist interpolation improves neuron yield in multiunit recordings

Timothy J. Blanche, Nicholas V. Swindale
<span title="">2006</span> <i title="Elsevier BV"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/huhco7lwxvct3fbbxk44mmpflu" style="color: black;">Journal of Neuroscience Methods</a> </i> &nbsp;
For most purposes, including spike sorting, sample rates below 25 kHz with bandlimited interpolation to 50 kHz were ideal, with negligible gains above this rate.  ...  Here we show that bandlimited interpolation with sample-and-hold delay correction reduces waveform variability, leading to improved reliability of threshold-based event detection and improved spike sorting  ...  (B) Uncentred spike amplitude clusters from another neuron (n = 1253). Underestimation of spike amplitudes produced the drift in cluster centres at low sample rates.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.jneumeth.2005.12.031">doi:10.1016/j.jneumeth.2005.12.031</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/16481043">pmid:16481043</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/nnt65jbwirbrjnmxsxynr5jfzy">fatcat:nnt65jbwirbrjnmxsxynr5jfzy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170812084629/http://www.swindale.ecc.ubc.ca/Publications?action=AttachFile&amp;do=get&amp;target=nyquist_interpolation.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/f2/4a/f24a7dc4dff0d5bd94a0ecc16c6564863960193f.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.jneumeth.2005.12.031"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> elsevier.com </button> </a>

Solving Constraint Satisfaction Problems with Networks of Spiking Neurons

Zeno Jonke, Stefan Habenschuss, Wolfgang Maass
<span title="2016-03-30">2016</span> <i title="Frontiers Media SA"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/wrk3kouosrhcxiprcbguskdipu" style="color: black;">Frontiers in Neuroscience</a> </i> &nbsp;
machines) and Gibbs sampling.  ...  Such spike-based computations promise to be substantially more power-efficient than traditional clocked processing schemes.  ...  Our theoretical analysis implies that this effect enhances exploration in spike-based networks, compared with Boltzmann machines (Gibbs sampling).  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3389/fnins.2016.00118">doi:10.3389/fnins.2016.00118</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/27065785">pmid:27065785</a> <a target="_blank" rel="external noopener" href="https://pubmed.ncbi.nlm.nih.gov/PMC4811945/">pmcid:PMC4811945</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ecdskaa5f5h2hbjhiu3wr5rqrq">fatcat:ecdskaa5f5h2hbjhiu3wr5rqrq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170830020609/https://fjfsdata01prod.blob.core.windows.net/articles/files/156676/pubmed-zip/.versions/1/.package-entries/fnins-10-00118/fnins-10-00118.pdf?sv=2015-12-11&amp;sr=b&amp;sig=Tqf5z30c9s6ohjZf8w64hx3%2Bi72nwjMHRZR0TlkZYo0%3D&amp;se=2017-08-30T02%3A06%3A15Z&amp;sp=r&amp;rscd=attachment%3B%20filename%2A%3DUTF-8%27%27fnins-10-00118.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/c9/4b/c94b909606fa980dd4dde8cb3afd3bba9efae217.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3389/fnins.2016.00118"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> frontiersin.org </button> </a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4811945" title="pubmed link"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> pubmed.gov </button> </a>

A theoretical basis for efficient computations with noisy spiking neurons [article]

Zeno Jonke, Stefan Habenschuss, Wolfgang Maass
<span title="2014-12-18">2014</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Furthermore, one can demonstrate for the Traveling Salesman Problem a surprising computational advantage of networks of spiking neurons compared with traditional artificial neural networks and Gibbs sampling  ...  Such spike-based computations promise to be substantially more power-efficient than traditional clocked processing schemes.  ...  Powerful computations with spiking neurons have previously been demonstrated in [9] .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1412.5862v1">arXiv:1412.5862v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/qfg7wp4b75hllkoye2x45zt4ei">fatcat:qfg7wp4b75hllkoye2x45zt4ei</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200928184015/https://arxiv.org/pdf/1412.5862v1.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/01/fa/01fa109794ce5cf14a47565947e98898520788c1.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1412.5862v1" 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>

Neuromorphic Processing and Sensing: Evolutionary Progression of AI to Spiking [article]

Philippe Reiter, Geet Rose Jose, Spyridon Bizmpikis, Ionela-Ancuţa Cîrjilă
<span title="2020-07-10">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Neuromorphic technologies based on Spiking Neural Network algorithms hold the promise to implement advanced artificial intelligence using a fraction of the computations and power requirements by modeling  ...  the functioning, and spiking, of the human brain.  ...  to also leverage low-power, low-latency and highly parallel SNN models, where appropriate.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2007.05606v1">arXiv:2007.05606v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/mw7nczubnzao3l73kyibxyvjpy">fatcat:mw7nczubnzao3l73kyibxyvjpy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200721151418/https://arxiv.org/ftp/arxiv/papers/2007/2007.05606.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/2007.05606v1" 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>
&laquo; Previous Showing results 1 &mdash; 15 out of 654 results