FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2765399440> ?p ?o ?g. }

• W2765399440 endingPage "4302" @default.
• W2765399440 startingPage "4287" @default.
• W2765399440 abstract "In this paper, we propose an online learning algorithm for supervised learning in multilayer spiking neural networks (SNNs). It is found that the spike timings of neurons in an SNN can be exploited to estimate the gradients that are associated with each synapse. With the proposed method of estimating gradients, learning similar to the stochastic gradient descent process employed in a conventional artificial neural network (ANN) can be achieved. In addition to the conventional layer-by-layer backpropagation, a one-pass direct backpropagation is possible using the proposed learning algorithm. Two neural networks, with one and two hidden layers, are employed as examples to demonstrate the effectiveness of the proposed learning algorithms. Several techniques for more effective learning are discussed, including utilizing a random refractory period to avoid saturation of spikes, employing a quantization noise injection technique and pseudorandom initial conditions to decorrelate spike timings, in addition to leveraging the progressive precision in an SNN to reduce the inference latency and energy. Extensive parametric simulations are conducted to examine the aforementioned techniques. The learning algorithm is developed with the considerations of ease of hardware implementation and relative compatibility with the classic ANN-based learning. Therefore, the proposed algorithm not only enjoys the high energy efficiency and good scalability of an SNN in its specialized hardware but also benefits from the well-developed theory and techniques of conventional ANN-based learning. The Modified National Institute of Standards and Technology database benchmark test is conducted to verify the newly proposed learning algorithm. Classification correct rates of 97.2% and 97.8% are achieved for the one-hidden-layer and two-hidden-layer neural networks, respectively. Moreover, a brief discussion of the hardware implementations is presented for two mainstream architectures." @default.
• W2765399440 created "2017-11-10" @default.
• W2765399440 creator A5056303339 @default.
• W2765399440 creator A5068645158 @default.
• W2765399440 date "2018-09-01" @default.
• W2765399440 modified "2023-10-15" @default.
• W2765399440 title "Online Supervised Learning for Hardware-Based Multilayer Spiking Neural Networks Through the Modulation of Weight-Dependent Spike-Timing-Dependent Plasticity" @default.
• W2765399440 cites W1570411240 @default.
• W2765399440 cites W1645800954 @default.
• W2765399440 cites W1926340497 @default.
• W2765399440 cites W1970974872 @default.
• W2765399440 cites W2003056114 @default.
• W2765399440 cites W2007815184 @default.
• W2765399440 cites W2008008156 @default.
• W2765399440 cites W2015724439 @default.
• W2765399440 cites W2016922062 @default.
• W2765399440 cites W2018915052 @default.
• W2765399440 cites W2020676607 @default.
• W2765399440 cites W2045614943 @default.
• W2765399440 cites W2051601318 @default.
• W2765399440 cites W2060956313 @default.
• W2765399440 cites W2074589580 @default.
• W2765399440 cites W2079995124 @default.
• W2765399440 cites W2086066258 @default.
• W2765399440 cites W2092268242 @default.
• W2765399440 cites W2092618119 @default.
• W2765399440 cites W2095725009 @default.
• W2765399440 cites W2112181056 @default.
• W2765399440 cites W2112796928 @default.
• W2765399440 cites W2115831804 @default.
• W2765399440 cites W2130360162 @default.
• W2765399440 cites W2130974072 @default.
• W2765399440 cites W2136922672 @default.
• W2765399440 cites W2138913040 @default.
• W2765399440 cites W2147030841 @default.
• W2765399440 cites W2155377787 @default.
• W2765399440 cites W2162827630 @default.
• W2765399440 cites W2163288878 @default.
• W2765399440 cites W2165396124 @default.
• W2765399440 cites W2165639766 @default.
• W2765399440 cites W2316169433 @default.
• W2765399440 cites W2464569091 @default.
• W2765399440 cites W2485281439 @default.
• W2765399440 cites W2569813014 @default.
• W2765399440 cites W44815768 @default.
• W2765399440 doi "https://doi.org/10.1109/tnnls.2017.2761335" @default.
• W2765399440 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/29990088" @default.
• W2765399440 hasPublicationYear "2018" @default.
• W2765399440 type Work @default.
• W2765399440 sameAs 2765399440 @default.
• W2765399440 citedByCount "35" @default.
• W2765399440 countsByYear W27653994402017 @default.
• W2765399440 countsByYear W27653994402018 @default.
• W2765399440 countsByYear W27653994402019 @default.
• W2765399440 countsByYear W27653994402020 @default.
• W2765399440 countsByYear W27653994402021 @default.
• W2765399440 countsByYear W27653994402022 @default.
• W2765399440 countsByYear W27653994402023 @default.
• W2765399440 crossrefType "journal-article" @default.
• W2765399440 hasAuthorship W2765399440A5056303339 @default.
• W2765399440 hasAuthorship W2765399440A5068645158 @default.
• W2765399440 hasBestOaLocation W27653994401 @default.
• W2765399440 hasConcept C11413529 @default.
• W2765399440 hasConcept C11731999 @default.
• W2765399440 hasConcept C119857082 @default.
• W2765399440 hasConcept C136389625 @default.
• W2765399440 hasConcept C151927369 @default.
• W2765399440 hasConcept C154945302 @default.
• W2765399440 hasConcept C155032097 @default.
• W2765399440 hasConcept C206688291 @default.
• W2765399440 hasConcept C41008148 @default.
• W2765399440 hasConcept C48044578 @default.
• W2765399440 hasConcept C50644808 @default.
• W2765399440 hasConcept C77088390 @default.
• W2765399440 hasConceptScore W2765399440C11413529 @default.
• W2765399440 hasConceptScore W2765399440C11731999 @default.
• W2765399440 hasConceptScore W2765399440C119857082 @default.
• W2765399440 hasConceptScore W2765399440C136389625 @default.
• W2765399440 hasConceptScore W2765399440C151927369 @default.
• W2765399440 hasConceptScore W2765399440C154945302 @default.
• W2765399440 hasConceptScore W2765399440C155032097 @default.
• W2765399440 hasConceptScore W2765399440C206688291 @default.
• W2765399440 hasConceptScore W2765399440C41008148 @default.
• W2765399440 hasConceptScore W2765399440C48044578 @default.
• W2765399440 hasConceptScore W2765399440C50644808 @default.
• W2765399440 hasConceptScore W2765399440C77088390 @default.
• W2765399440 hasFunder F4320337392 @default.
• W2765399440 hasIssue "9" @default.
• W2765399440 hasLocation W27653994401 @default.
• W2765399440 hasLocation W27653994402 @default.
• W2765399440 hasOpenAccess W2765399440 @default.
• W2765399440 hasPrimaryLocation W27653994401 @default.
• W2765399440 hasRelatedWork W2064384291 @default.
• W2765399440 hasRelatedWork W2150389614 @default.
• W2765399440 hasRelatedWork W2443530087 @default.
• W2765399440 hasRelatedWork W2480330148 @default.
• W2765399440 hasRelatedWork W2972809290 @default.
• W2765399440 hasRelatedWork W3157537181 @default.

• next