Matches in SemOpenAlex for { <https://semopenalex.org/work/W3212204808> ?p ?o ?g. }
- W3212204808 endingPage "1491" @default.
- W3212204808 startingPage "1491" @default.
- W3212204808 abstract "Traditional machine-learning methods are inefficient in capturing chaos in nonlinear dynamical systems, especially when the time difference Δt between consecutive steps is so large that the extracted time series looks apparently random. Here, we introduce a new long-short-term-memory (LSTM)-based recurrent architecture by tensorizing the cell-state-to-state propagation therein, maintaining the long-term memory feature of LSTM, while simultaneously enhancing the learning of short-term nonlinear complexity. We stress that the global minima of training can be most efficiently reached by our tensor structure where all nonlinear terms, up to some polynomial order, are treated explicitly and weighted equally. The efficiency and generality of our architecture are systematically investigated and tested through theoretical analysis and experimental examinations. In our design, we have explicitly used two different many-body entanglement structures-matrix product states (MPS) and the multiscale entanglement renormalization ansatz (MERA)-as physics-inspired tensor decomposition techniques, from which we find that MERA generally performs better than MPS, hence conjecturing that the learnability of chaos is determined not only by the number of free parameters but also the tensor complexity-recognized as how entanglement entropy scales with varying matricization of the tensor." @default.
- W3212204808 created "2021-11-22" @default.
- W3212204808 creator A5007991036 @default.
- W3212204808 creator A5061980190 @default.
- W3212204808 date "2021-11-11" @default.
- W3212204808 modified "2023-10-01" @default.
- W3212204808 title "Entanglement-Structured LSTM Boosts Chaotic Time Series Forecasting" @default.
- W3212204808 cites W1858056047 @default.
- W3212204808 cites W1922629554 @default.
- W3212204808 cites W1972710509 @default.
- W3212204808 cites W1987377268 @default.
- W3212204808 cites W2000061362 @default.
- W3212204808 cites W2018397720 @default.
- W3212204808 cites W2038198231 @default.
- W3212204808 cites W2040395995 @default.
- W3212204808 cites W2064675550 @default.
- W3212204808 cites W2066972040 @default.
- W3212204808 cites W2093774709 @default.
- W3212204808 cites W2105594594 @default.
- W3212204808 cites W2118756059 @default.
- W3212204808 cites W2560817176 @default.
- W3212204808 cites W2782714865 @default.
- W3212204808 cites W2794778778 @default.
- W3212204808 cites W2919115771 @default.
- W3212204808 cites W2923537029 @default.
- W3212204808 cites W2942828225 @default.
- W3212204808 cites W2965152585 @default.
- W3212204808 cites W2982612860 @default.
- W3212204808 cites W2998483963 @default.
- W3212204808 cites W2998647565 @default.
- W3212204808 cites W3046071206 @default.
- W3212204808 cites W3105919389 @default.
- W3212204808 doi "https://doi.org/10.3390/e23111491" @default.
- W3212204808 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/8626053" @default.
- W3212204808 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/34828189" @default.
- W3212204808 hasPublicationYear "2021" @default.
- W3212204808 type Work @default.
- W3212204808 sameAs 3212204808 @default.
- W3212204808 citedByCount "3" @default.
- W3212204808 countsByYear W32122048082022 @default.
- W3212204808 countsByYear W32122048082023 @default.
- W3212204808 crossrefType "journal-article" @default.
- W3212204808 hasAuthorship W3212204808A5007991036 @default.
- W3212204808 hasAuthorship W3212204808A5061980190 @default.
- W3212204808 hasBestOaLocation W32122048081 @default.
- W3212204808 hasConcept C11413529 @default.
- W3212204808 hasConcept C121040770 @default.
- W3212204808 hasConcept C121332964 @default.
- W3212204808 hasConcept C121864883 @default.
- W3212204808 hasConcept C130979935 @default.
- W3212204808 hasConcept C143724316 @default.
- W3212204808 hasConcept C151730666 @default.
- W3212204808 hasConcept C154945302 @default.
- W3212204808 hasConcept C158622935 @default.
- W3212204808 hasConcept C2777052490 @default.
- W3212204808 hasConcept C28826006 @default.
- W3212204808 hasConcept C33923547 @default.
- W3212204808 hasConcept C37914503 @default.
- W3212204808 hasConcept C41008148 @default.
- W3212204808 hasConcept C62520636 @default.
- W3212204808 hasConcept C80444323 @default.
- W3212204808 hasConcept C84114770 @default.
- W3212204808 hasConcept C86803240 @default.
- W3212204808 hasConceptScore W3212204808C11413529 @default.
- W3212204808 hasConceptScore W3212204808C121040770 @default.
- W3212204808 hasConceptScore W3212204808C121332964 @default.
- W3212204808 hasConceptScore W3212204808C121864883 @default.
- W3212204808 hasConceptScore W3212204808C130979935 @default.
- W3212204808 hasConceptScore W3212204808C143724316 @default.
- W3212204808 hasConceptScore W3212204808C151730666 @default.
- W3212204808 hasConceptScore W3212204808C154945302 @default.
- W3212204808 hasConceptScore W3212204808C158622935 @default.
- W3212204808 hasConceptScore W3212204808C2777052490 @default.
- W3212204808 hasConceptScore W3212204808C28826006 @default.
- W3212204808 hasConceptScore W3212204808C33923547 @default.
- W3212204808 hasConceptScore W3212204808C37914503 @default.
- W3212204808 hasConceptScore W3212204808C41008148 @default.
- W3212204808 hasConceptScore W3212204808C62520636 @default.
- W3212204808 hasConceptScore W3212204808C80444323 @default.
- W3212204808 hasConceptScore W3212204808C84114770 @default.
- W3212204808 hasConceptScore W3212204808C86803240 @default.
- W3212204808 hasIssue "11" @default.
- W3212204808 hasLocation W32122048081 @default.
- W3212204808 hasLocation W32122048082 @default.
- W3212204808 hasLocation W32122048083 @default.
- W3212204808 hasLocation W32122048084 @default.
- W3212204808 hasOpenAccess W3212204808 @default.
- W3212204808 hasPrimaryLocation W32122048081 @default.
- W3212204808 hasRelatedWork W1499618656 @default.
- W3212204808 hasRelatedWork W2007468112 @default.
- W3212204808 hasRelatedWork W2026265139 @default.
- W3212204808 hasRelatedWork W2034065402 @default.
- W3212204808 hasRelatedWork W2244270523 @default.
- W3212204808 hasRelatedWork W2265293705 @default.
- W3212204808 hasRelatedWork W2785977580 @default.
- W3212204808 hasRelatedWork W3098656521 @default.
- W3212204808 hasRelatedWork W4280550370 @default.
- W3212204808 hasRelatedWork W75985283 @default.