FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2942334036> ?p ?o ?g. }

• W2942334036 endingPage "301" @default.
• W2942334036 startingPage "291" @default.
• W2942334036 abstract "Recurrent Neural Networks such as Long Short-Term Memory (LSTM) and Gated Recurrent Units (GRUs) are often deployed as neural network-based predictors for time series data. Recently, Hierarchical Temporal Memory (HTM), a machine learning technology attempting to simulate the human brain’s neocortex, has been proposed as another approach to time series data prediction. While HTM has gained a lot of attention, little is known about the actual performance compared to the more common RNNs. The only performance comparison between the two, performed at the company behind HTM, shows they perform similarly. In this article, we present a more in-depth performance comparison, involving more extensive hyperparameter tuning and evaluation on more scenarios. Surprisingly, our results show that both LSTM and GRUs can outperform HTM by over 30% at lower runtime. Furthermore, we show that HTM requires explicitly timestamped data to recognize daily and weekly patterns, while LSTM only needs the raw sequential data to predict such time series accurately. Finally, our experiments indicate that the temporally aware components of all considered predictors contribute nothing to the prediction accuracy. We further strengthen this claim by presenting equally or better performing Multilayer Perceptrons conceptually similar to the HTM and LSTM, disregarding their temporal aspects." @default.
• W2942334036 created "2019-05-03" @default.
• W2942334036 creator A5035645727 @default.
• W2942334036 creator A5049021976 @default.
• W2942334036 date "2020-07-01" @default.
• W2942334036 modified "2023-10-17" @default.
• W2942334036 title "Hierarchical temporal memory and recurrent neural networks for time series prediction: An empirical validation and reduction to multilayer perceptrons" @default.
• W2942334036 cites W1069790386 @default.
• W2942334036 cites W1586335931 @default.
• W2942334036 cites W1689711448 @default.
• W2942334036 cites W1968140153 @default.
• W2942334036 cites W1977177161 @default.
• W2942334036 cites W2010611103 @default.
• W2942334036 cites W2012079387 @default.
• W2942334036 cites W2016210396 @default.
• W2942334036 cites W2024155197 @default.
• W2942334036 cites W2032927332 @default.
• W2942334036 cites W2037883917 @default.
• W2942334036 cites W2041155726 @default.
• W2942334036 cites W2057653135 @default.
• W2942334036 cites W2059776567 @default.
• W2942334036 cites W2064675550 @default.
• W2942334036 cites W2067688816 @default.
• W2942334036 cites W2069315453 @default.
• W2942334036 cites W2083022762 @default.
• W2942334036 cites W2085463545 @default.
• W2942334036 cites W2105934661 @default.
• W2942334036 cites W2106069155 @default.
• W2942334036 cites W2108537597 @default.
• W2942334036 cites W2131403095 @default.
• W2942334036 cites W2136848157 @default.
• W2942334036 cites W2149320615 @default.
• W2942334036 cites W2150722745 @default.
• W2942334036 cites W2171234954 @default.
• W2942334036 cites W2178055113 @default.
• W2942334036 cites W2201004764 @default.
• W2942334036 cites W222543348 @default.
• W2942334036 cites W2412230368 @default.
• W2942334036 cites W2573587735 @default.
• W2942334036 cites W2580792538 @default.
• W2942334036 cites W2598743429 @default.
• W2942334036 cites W2750971660 @default.
• W2942334036 cites W2753802340 @default.
• W2942334036 cites W2755624369 @default.
• W2942334036 cites W2759669842 @default.
• W2942334036 cites W2792756593 @default.
• W2942334036 cites W2801430831 @default.
• W2942334036 cites W2804129310 @default.
• W2942334036 cites W2950860789 @default.
• W2942334036 cites W2964284952 @default.
• W2942334036 doi "https://doi.org/10.1016/j.neucom.2018.09.098" @default.
• W2942334036 hasPublicationYear "2020" @default.
• W2942334036 type Work @default.
• W2942334036 sameAs 2942334036 @default.
• W2942334036 citedByCount "29" @default.
• W2942334036 countsByYear W29423340362019 @default.
• W2942334036 countsByYear W29423340362020 @default.
• W2942334036 countsByYear W29423340362021 @default.
• W2942334036 countsByYear W29423340362022 @default.
• W2942334036 countsByYear W29423340362023 @default.
• W2942334036 crossrefType "journal-article" @default.
• W2942334036 hasAuthorship W2942334036A5035645727 @default.
• W2942334036 hasAuthorship W2942334036A5049021976 @default.
• W2942334036 hasConcept C119857082 @default.
• W2942334036 hasConcept C143724316 @default.
• W2942334036 hasConcept C147168706 @default.
• W2942334036 hasConcept C151406439 @default.
• W2942334036 hasConcept C151730666 @default.
• W2942334036 hasConcept C154945302 @default.
• W2942334036 hasConcept C41008148 @default.
• W2942334036 hasConcept C50644808 @default.
• W2942334036 hasConcept C60908668 @default.
• W2942334036 hasConcept C8642999 @default.
• W2942334036 hasConcept C86803240 @default.
• W2942334036 hasConceptScore W2942334036C119857082 @default.
• W2942334036 hasConceptScore W2942334036C143724316 @default.
• W2942334036 hasConceptScore W2942334036C147168706 @default.
• W2942334036 hasConceptScore W2942334036C151406439 @default.
• W2942334036 hasConceptScore W2942334036C151730666 @default.
• W2942334036 hasConceptScore W2942334036C154945302 @default.
• W2942334036 hasConceptScore W2942334036C41008148 @default.
• W2942334036 hasConceptScore W2942334036C50644808 @default.
• W2942334036 hasConceptScore W2942334036C60908668 @default.
• W2942334036 hasConceptScore W2942334036C8642999 @default.
• W2942334036 hasConceptScore W2942334036C86803240 @default.
• W2942334036 hasLocation W29423340361 @default.
• W2942334036 hasOpenAccess W2942334036 @default.
• W2942334036 hasPrimaryLocation W29423340361 @default.
• W2942334036 hasRelatedWork W2120684500 @default.
• W2942334036 hasRelatedWork W2996568036 @default.
• W2942334036 hasRelatedWork W3137262131 @default.
• W2942334036 hasRelatedWork W4210794429 @default.
• W2942334036 hasRelatedWork W4212859008 @default.
• W2942334036 hasRelatedWork W4280535922 @default.
• W2942334036 hasRelatedWork W4295309597 @default.
• W2942334036 hasRelatedWork W4304128395 @default.
• W2942334036 hasRelatedWork W4366674482 @default.
• W2942334036 hasRelatedWork W2134481421 @default.

• next