Matches in SemOpenAlex for { <https://semopenalex.org/work/W3128383816> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W3128383816 abstract "This paper explores the benefit of added noise in increasing the computational complexity of digital recurrent neural networks (RNNs). The physically accepted model of the universe imposes rational number, stochastic limits on all calculations. An analog RNN with those limits calculates at the super-Turing complexity level BPP/log*. In this paper, we demonstrate how noise aids digital RNNs in attaining super-Turing operation similar to analog RNNs. We investigate moving limited-precision systems from not being chaotic at small amounts of noise, through consistency with chaos, to overwhelming it at large amounts of noise. A Kolmogorov-complexity-based proof shows that an infinite computational class hierarchy exists between P, the Turing class, and BPP/log*. The hierarchy offers a possibility that the noise-enhanced digital RNNs could operate at a super-Turing level less complex than BPP/log*. As the uniform noise increases, the digital RNNs develop positive Lyapunov exponents intimating that chaos is mimicked. The exponents maximize to the accepted values for the logistic and Hénon maps when the noise equals eight times the least significant bit of the noisy recurrent signals for the logistic digital RNN and four times the Hénon digital RNN.Received 21 November 2019Accepted 21 January 2021DOI:https://doi.org/10.1103/PhysRevResearch.3.013120Published by the American Physical Society under the terms of the Creative Commons Attribution 4.0 International license. Further distribution of this work must maintain attribution to the author(s) and the published article's title, journal citation, and DOI.Published by the American Physical SocietyPhysics Subject Headings (PhySH)Research AreasComputational complexityDynamics of networksNoiseTechniquesChaos & nonlinear dynamicsNonlinear DynamicsInterdisciplinary PhysicsStatistical Physics" @default.
- W3128383816 created "2021-02-15" @default.
- W3128383816 creator A5020306330 @default.
- W3128383816 creator A5040578359 @default.
- W3128383816 creator A5049624531 @default.
- W3128383816 date "2021-02-08" @default.
- W3128383816 modified "2023-09-23" @default.
- W3128383816 title "Noise optimizes super-Turing computation in recurrent neural networks" @default.
- W3128383816 cites W1855879034 @default.
- W3128383816 cites W1982491809 @default.
- W3128383816 cites W1994739656 @default.
- W3128383816 cites W2047164342 @default.
- W3128383816 cites W2053429109 @default.
- W3128383816 cites W2068501389 @default.
- W3128383816 cites W2071935149 @default.
- W3128383816 cites W2075841129 @default.
- W3128383816 cites W2079483931 @default.
- W3128383816 cites W2099977515 @default.
- W3128383816 cites W2116967254 @default.
- W3128383816 cites W2124428761 @default.
- W3128383816 cites W2126160338 @default.
- W3128383816 cites W2127604727 @default.
- W3128383816 cites W2141969391 @default.
- W3128383816 cites W2151007095 @default.
- W3128383816 cites W2211778065 @default.
- W3128383816 cites W2727375987 @default.
- W3128383816 cites W2765310599 @default.
- W3128383816 cites W4232367939 @default.
- W3128383816 cites W51799866 @default.
- W3128383816 doi "https://doi.org/10.1103/physrevresearch.3.013120" @default.
- W3128383816 hasPublicationYear "2021" @default.
- W3128383816 type Work @default.
- W3128383816 sameAs 3128383816 @default.
- W3128383816 citedByCount "2" @default.
- W3128383816 countsByYear W31283838162021 @default.
- W3128383816 crossrefType "journal-article" @default.
- W3128383816 hasAuthorship W3128383816A5020306330 @default.
- W3128383816 hasAuthorship W3128383816A5040578359 @default.
- W3128383816 hasAuthorship W3128383816A5049624531 @default.
- W3128383816 hasBestOaLocation W31283838161 @default.
- W3128383816 hasConcept C11413529 @default.
- W3128383816 hasConcept C115961682 @default.
- W3128383816 hasConcept C131671149 @default.
- W3128383816 hasConcept C147168706 @default.
- W3128383816 hasConcept C154945302 @default.
- W3128383816 hasConcept C199360897 @default.
- W3128383816 hasConcept C2777052490 @default.
- W3128383816 hasConcept C29248071 @default.
- W3128383816 hasConcept C41008148 @default.
- W3128383816 hasConcept C45374587 @default.
- W3128383816 hasConcept C48415503 @default.
- W3128383816 hasConcept C50644808 @default.
- W3128383816 hasConcept C80444323 @default.
- W3128383816 hasConcept C9870796 @default.
- W3128383816 hasConcept C99498987 @default.
- W3128383816 hasConceptScore W3128383816C11413529 @default.
- W3128383816 hasConceptScore W3128383816C115961682 @default.
- W3128383816 hasConceptScore W3128383816C131671149 @default.
- W3128383816 hasConceptScore W3128383816C147168706 @default.
- W3128383816 hasConceptScore W3128383816C154945302 @default.
- W3128383816 hasConceptScore W3128383816C199360897 @default.
- W3128383816 hasConceptScore W3128383816C2777052490 @default.
- W3128383816 hasConceptScore W3128383816C29248071 @default.
- W3128383816 hasConceptScore W3128383816C41008148 @default.
- W3128383816 hasConceptScore W3128383816C45374587 @default.
- W3128383816 hasConceptScore W3128383816C48415503 @default.
- W3128383816 hasConceptScore W3128383816C50644808 @default.
- W3128383816 hasConceptScore W3128383816C80444323 @default.
- W3128383816 hasConceptScore W3128383816C9870796 @default.
- W3128383816 hasConceptScore W3128383816C99498987 @default.
- W3128383816 hasIssue "1" @default.
- W3128383816 hasLocation W31283838161 @default.
- W3128383816 hasLocation W31283838162 @default.
- W3128383816 hasOpenAccess W3128383816 @default.
- W3128383816 hasPrimaryLocation W31283838161 @default.
- W3128383816 hasRelatedWork W1483817375 @default.
- W3128383816 hasRelatedWork W1527973804 @default.
- W3128383816 hasRelatedWork W1556623397 @default.
- W3128383816 hasRelatedWork W2038569833 @default.
- W3128383816 hasRelatedWork W2063572548 @default.
- W3128383816 hasRelatedWork W2091072994 @default.
- W3128383816 hasRelatedWork W2116825378 @default.
- W3128383816 hasRelatedWork W2401794038 @default.
- W3128383816 hasRelatedWork W4255638962 @default.
- W3128383816 hasRelatedWork W4293150887 @default.
- W3128383816 hasVolume "3" @default.
- W3128383816 isParatext "false" @default.
- W3128383816 isRetracted "false" @default.
- W3128383816 magId "3128383816" @default.
- W3128383816 workType "article" @default.