Matches in SemOpenAlex for { <https://semopenalex.org/work/W4285157836> ?p ?o ?g. }
- W4285157836 endingPage "1" @default.
- W4285157836 startingPage "1" @default.
- W4285157836 abstract "Complicated temporal patterns can provide important information for accurate time series forecasting. Existing long short-term memory (LSTM) model with attention mechanism have achieved significant performance. However, the exponential decay of long-term memory of LSTM has not be resolved yet in these efforts, remaining a longstanding open problem in recurrent nature. This problem exhibits a bottleneck which restricts the performance of existing studies. Recently, spiking neural networks (SNNs) have shown high efficiency in capturing temporal patterns via the surrogate gradient (SG) method to resolve this issue. However, the concept-drift environment makes it impossible to pre-set the variance into the standard SG method due to time-varying data distribution. In this paper, we propose a novel adaptive and hybrid spiking (AHS) module embedded LSTM, collaborating with two attention mechanisms (called HSN-LSTM) to resolve above-mentioned problems. First, the AHS module is analyzed theoretically can remain long-term memory. Moreover, our smooth SG method avoids pre-setting of variance, which is not sensitive in the above scenarios. Besides, we use the negative log-likelihood function to adjust the attention score for alleviating the negative impact from the concept-drift. Experiment results show the HSN-LSTM outperformed the state-of-the-art models on several multivariate time series datasets." @default.
- W4285157836 created "2022-07-14" @default.
- W4285157836 creator A5019096648 @default.
- W4285157836 creator A5023918894 @default.
- W4285157836 creator A5045067652 @default.
- W4285157836 creator A5046934851 @default.
- W4285157836 creator A5047977430 @default.
- W4285157836 date "2022-01-01" @default.
- W4285157836 modified "2023-09-27" @default.
- W4285157836 title "A Hybrid Spiking Neurons Embedded LSTM Network for Multivariate Time Series Learning under Concept-drift Environment" @default.
- W4285157836 cites W2016646227 @default.
- W4285157836 cites W2064675550 @default.
- W4285157836 cites W2293918375 @default.
- W4285157836 cites W2613328025 @default.
- W4285157836 cites W2805852360 @default.
- W4285157836 cites W2811266412 @default.
- W4285157836 cites W2888109343 @default.
- W4285157836 cites W2892077605 @default.
- W4285157836 cites W2892632544 @default.
- W4285157836 cites W2905470007 @default.
- W4285157836 cites W2950445386 @default.
- W4285157836 cites W2963479420 @default.
- W4285157836 cites W2964347220 @default.
- W4285157836 cites W2966714118 @default.
- W4285157836 cites W2971659559 @default.
- W4285157836 cites W2984844508 @default.
- W4285157836 cites W2986815055 @default.
- W4285157836 cites W2993122943 @default.
- W4285157836 cites W2997848713 @default.
- W4285157836 cites W3034923703 @default.
- W4285157836 cites W3039829398 @default.
- W4285157836 cites W3046044791 @default.
- W4285157836 cites W3065747603 @default.
- W4285157836 cites W3080253043 @default.
- W4285157836 cites W3101383241 @default.
- W4285157836 cites W3102015031 @default.
- W4285157836 cites W3102750118 @default.
- W4285157836 cites W3108036060 @default.
- W4285157836 cites W3184526936 @default.
- W4285157836 cites W3206817059 @default.
- W4285157836 cites W3209387005 @default.
- W4285157836 cites W4238614602 @default.
- W4285157836 doi "https://doi.org/10.1109/tkde.2022.3178176" @default.
- W4285157836 hasPublicationYear "2022" @default.
- W4285157836 type Work @default.
- W4285157836 citedByCount "5" @default.
- W4285157836 countsByYear W42851578362022 @default.
- W4285157836 countsByYear W42851578362023 @default.
- W4285157836 crossrefType "journal-article" @default.
- W4285157836 hasAuthorship W4285157836A5019096648 @default.
- W4285157836 hasAuthorship W4285157836A5023918894 @default.
- W4285157836 hasAuthorship W4285157836A5045067652 @default.
- W4285157836 hasAuthorship W4285157836A5046934851 @default.
- W4285157836 hasAuthorship W4285157836A5047977430 @default.
- W4285157836 hasConcept C11731999 @default.
- W4285157836 hasConcept C119857082 @default.
- W4285157836 hasConcept C121332964 @default.
- W4285157836 hasConcept C121955636 @default.
- W4285157836 hasConcept C133488467 @default.
- W4285157836 hasConcept C143724316 @default.
- W4285157836 hasConcept C144133560 @default.
- W4285157836 hasConcept C147168706 @default.
- W4285157836 hasConcept C149635348 @default.
- W4285157836 hasConcept C151406439 @default.
- W4285157836 hasConcept C151730666 @default.
- W4285157836 hasConcept C153180895 @default.
- W4285157836 hasConcept C154945302 @default.
- W4285157836 hasConcept C161584116 @default.
- W4285157836 hasConcept C196083921 @default.
- W4285157836 hasConcept C2780513914 @default.
- W4285157836 hasConcept C41008148 @default.
- W4285157836 hasConcept C50644808 @default.
- W4285157836 hasConcept C60777511 @default.
- W4285157836 hasConcept C61797465 @default.
- W4285157836 hasConcept C62520636 @default.
- W4285157836 hasConcept C86803240 @default.
- W4285157836 hasConcept C89198739 @default.
- W4285157836 hasConceptScore W4285157836C11731999 @default.
- W4285157836 hasConceptScore W4285157836C119857082 @default.
- W4285157836 hasConceptScore W4285157836C121332964 @default.
- W4285157836 hasConceptScore W4285157836C121955636 @default.
- W4285157836 hasConceptScore W4285157836C133488467 @default.
- W4285157836 hasConceptScore W4285157836C143724316 @default.
- W4285157836 hasConceptScore W4285157836C144133560 @default.
- W4285157836 hasConceptScore W4285157836C147168706 @default.
- W4285157836 hasConceptScore W4285157836C149635348 @default.
- W4285157836 hasConceptScore W4285157836C151406439 @default.
- W4285157836 hasConceptScore W4285157836C151730666 @default.
- W4285157836 hasConceptScore W4285157836C153180895 @default.
- W4285157836 hasConceptScore W4285157836C154945302 @default.
- W4285157836 hasConceptScore W4285157836C161584116 @default.
- W4285157836 hasConceptScore W4285157836C196083921 @default.
- W4285157836 hasConceptScore W4285157836C2780513914 @default.
- W4285157836 hasConceptScore W4285157836C41008148 @default.
- W4285157836 hasConceptScore W4285157836C50644808 @default.
- W4285157836 hasConceptScore W4285157836C60777511 @default.
- W4285157836 hasConceptScore W4285157836C61797465 @default.
- W4285157836 hasConceptScore W4285157836C62520636 @default.