FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4285366309> ?p ?o ?g. }

• W4285366309 endingPage "37" @default.
• W4285366309 startingPage "1" @default.
• W4285366309 abstract "Artificial neural networks (ANN) trained by deep learning have shown tremendous success in audio, visual, and decision-making tasks. While these methods are loosely inspired by the brain, in terms of actual implementation, the similarity between mammalian brain and these algorithms is merely superficial. Moreover, more often than not, these algorithms require huge energy for real-world tasks due to their computation and memory heavy nature, which limits their potential application in energy-constrained scenarios. A prime reason for that is that unlike their biological counterparts, these algorithms were designed with the primary goal of increasing accuracy on some benchmark tasks. Spiking neural networks (SNN) bridge the gap between artificial algorithms and the biological model of brain due to their asynchronous spike-based signal processing model that closely resembles that of the brain. SNNs have drawn significant attention in recent years due to their energy efficiency, compatibility with low-power neuromorphic hardware, and event-based sensors. In this chapter, we give an exhaustive analysis of different learning algorithms proposed over past two decades for training SNNs. The proposed learning algorithms are broadly classified into two types: conversion-based and spike-based learning. The advantages, drawbacks, and potential application of each type of algorithms are systematically described. We also report on accuracy achieved by these algorithms in benchmark datasets. Recent works on learning algorithms and neuromorphic hardware implementations show that SNNs have the potential to reach state-of-the-art accuracy on several tasks at a fraction of energy cost compared to their deep learning counterparts." @default.
• W4285366309 created "2022-07-14" @default.
• W4285366309 creator A5002380437 @default.
• W4285366309 creator A5015481947 @default.
• W4285366309 date "2021-09-14" @default.
• W4285366309 modified "2023-09-24" @default.
• W4285366309 title "Neuromorphic Spiking Neural Network Algorithms" @default.
• W4285366309 cites W101771737 @default.
• W4285366309 cites W1486852018 @default.
• W4285366309 cites W1489333352 @default.
• W4285366309 cites W1531277577 @default.
• W4285366309 cites W1535810436 @default.
• W4285366309 cites W1545807718 @default.
• W4285366309 cites W1570411240 @default.
• W4285366309 cites W1620936430 @default.
• W4285366309 cites W1635512741 @default.
• W4285366309 cites W1645800954 @default.
• W4285366309 cites W1843946745 @default.
• W4285366309 cites W1965678517 @default.
• W4285366309 cites W1970109917 @default.
• W4285366309 cites W1982785464 @default.
• W4285366309 cites W1984541135 @default.
• W4285366309 cites W1984636010 @default.
• W4285366309 cites W1987994242 @default.
• W4285366309 cites W2001218774 @default.
• W4285366309 cites W2001619934 @default.
• W4285366309 cites W2018046340 @default.
• W4285366309 cites W2019306960 @default.
• W4285366309 cites W2020676607 @default.
• W4285366309 cites W2042013578 @default.
• W4285366309 cites W2052798315 @default.
• W4285366309 cites W2054113233 @default.
• W4285366309 cites W2065125569 @default.
• W4285366309 cites W2097117768 @default.
• W4285366309 cites W2101346672 @default.
• W4285366309 cites W2108598243 @default.
• W4285366309 cites W2112408199 @default.
• W4285366309 cites W2112796928 @default.
• W4285366309 cites W2113420865 @default.
• W4285366309 cites W2113536146 @default.
• W4285366309 cites W2115831804 @default.
• W4285366309 cites W2119644986 @default.
• W4285366309 cites W2126404188 @default.
• W4285366309 cites W2130360162 @default.
• W4285366309 cites W2130974072 @default.
• W4285366309 cites W2136922672 @default.
• W4285366309 cites W2138913040 @default.
• W4285366309 cites W2139053813 @default.
• W4285366309 cites W2142770417 @default.
• W4285366309 cites W2147101007 @default.
• W4285366309 cites W2151251384 @default.
• W4285366309 cites W2159110831 @default.
• W4285366309 cites W2160815625 @default.
• W4285366309 cites W2164610565 @default.
• W4285366309 cites W2165639766 @default.
• W4285366309 cites W2167148127 @default.
• W4285366309 cites W2168114164 @default.
• W4285366309 cites W2170968634 @default.
• W4285366309 cites W2183102254 @default.
• W4285366309 cites W2194775991 @default.
• W4285366309 cites W2257979135 @default.
• W4285366309 cites W2290982066 @default.
• W4285366309 cites W2516042576 @default.
• W4285366309 cites W2526044239 @default.
• W4285366309 cites W2552737632 @default.
• W4285366309 cites W2565565355 @default.
• W4285366309 cites W2569813014 @default.
• W4285366309 cites W2583316550 @default.
• W4285366309 cites W2621826044 @default.
• W4285366309 cites W2734358244 @default.
• W4285366309 cites W2754486806 @default.
• W4285366309 cites W2775079417 @default.
• W4285366309 cites W2779025322 @default.
• W4285366309 cites W2783525259 @default.
• W4285366309 cites W2788415486 @default.
• W4285366309 cites W2794061657 @default.
• W4285366309 cites W2795627216 @default.
• W4285366309 cites W2898323475 @default.
• W4285366309 cites W2919115771 @default.
• W4285366309 cites W2946092987 @default.
• W4285366309 cites W2962804204 @default.
• W4285366309 cites W2963037989 @default.
• W4285366309 cites W2963157821 @default.
• W4285366309 cites W2963868833 @default.
• W4285366309 cites W2964338223 @default.
• W4285366309 cites W2982158940 @default.
• W4285366309 cites W2990793844 @default.
• W4285366309 cites W4231081240 @default.
• W4285366309 cites W4238614602 @default.
• W4285366309 cites W4244471710 @default.
• W4285366309 doi "https://doi.org/10.1007/978-981-15-2848-4_44-1" @default.
• W4285366309 hasPublicationYear "2021" @default.
• W4285366309 type Work @default.
• W4285366309 citedByCount "0" @default.
• W4285366309 crossrefType "book-chapter" @default.
• W4285366309 hasAuthorship W4285366309A5002380437 @default.
• W4285366309 hasAuthorship W4285366309A5015481947 @default.
• W4285366309 hasConcept C105795698 @default.

• next