FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3037578981> ?p ?o ?g. }

• W3037578981 endingPage "083040" @default.
• W3037578981 startingPage "083040" @default.
• W3037578981 abstract "Abstract Adaptive systems—such as a biological organism gaining survival advantage, an autonomous robot executing a functional task, or a motor protein transporting intracellular nutrients—must somehow embody relevant regularities and stochasticity in their environments to take full advantage of thermodynamic resources. Analogously, but in a purely computational realm, machine learning algorithms estimate models to capture predictable structure and identify irrelevant noise in training data. This happens through optimization of performance metrics, such as model likelihood. If such learning is physically implemented, is there a sense in which computational models estimated through machine learning are physically preferred? We introduce the thermodynamic principle that work production is the most relevant performance measure for an adaptive physical agent and compare the results to the maximum-likelihood principle that guides machine learning. Within the class of physical agents that most efficiently harvest energy from their environment, we demonstrate that an efficient agent’s model explicitly determines its architecture and how much useful work it harvests from the environment. We then show that selecting the maximum-work agent for given environmental data corresponds to finding the maximum-likelihood model. This establishes an equivalence between nonequilibrium thermodynamics and dynamic learning. In this way, work maximization emerges as an organizing principle that underlies learning in adaptive thermodynamic systems." @default.
• W3037578981 created "2020-07-02" @default.
• W3037578981 creator A5024118330 @default.
• W3037578981 creator A5047565816 @default.
• W3037578981 creator A5084187489 @default.
• W3037578981 date "2022-08-01" @default.
• W3037578981 modified "2023-09-26" @default.
• W3037578981 title "Thermodynamic machine learning through maximum work production" @default.
• W3037578981 cites W1532729789 @default.
• W3037578981 cites W1537301082 @default.
• W3037578981 cites W1636243797 @default.
• W3037578981 cites W1776857128 @default.
• W3037578981 cites W1964777250 @default.
• W3037578981 cites W1984391316 @default.
• W3037578981 cites W1986041196 @default.
• W3037578981 cites W1992659707 @default.
• W3037578981 cites W1994665575 @default.
• W3037578981 cites W1998052201 @default.
• W3037578981 cites W2001616149 @default.
• W3037578981 cites W2021820673 @default.
• W3037578981 cites W2022731279 @default.
• W3037578981 cites W2024794609 @default.
• W3037578981 cites W2026799324 @default.
• W3037578981 cites W2028210598 @default.
• W3037578981 cites W2031451638 @default.
• W3037578981 cites W2032558547 @default.
• W3037578981 cites W2046945477 @default.
• W3037578981 cites W2047991033 @default.
• W3037578981 cites W2049633694 @default.
• W3037578981 cites W2059681180 @default.
• W3037578981 cites W2066261007 @default.
• W3037578981 cites W2071214852 @default.
• W3037578981 cites W2099530148 @default.
• W3037578981 cites W2108184883 @default.
• W3037578981 cites W2113501657 @default.
• W3037578981 cites W2115884551 @default.
• W3037578981 cites W2123088883 @default.
• W3037578981 cites W2126160338 @default.
• W3037578981 cites W2128706048 @default.
• W3037578981 cites W2136541099 @default.
• W3037578981 cites W2140971659 @default.
• W3037578981 cites W2149158279 @default.
• W3037578981 cites W2150872430 @default.
• W3037578981 cites W2467290685 @default.
• W3037578981 cites W2558967331 @default.
• W3037578981 cites W2560808830 @default.
• W3037578981 cites W2563135419 @default.
• W3037578981 cites W2752407383 @default.
• W3037578981 cites W2790922269 @default.
• W3037578981 cites W2896377340 @default.
• W3037578981 cites W2919115771 @default.
• W3037578981 cites W2949321739 @default.
• W3037578981 cites W2963003796 @default.
• W3037578981 cites W2993383518 @default.
• W3037578981 cites W2996141621 @default.
• W3037578981 cites W3033917160 @default.
• W3037578981 cites W3041086464 @default.
• W3037578981 cites W3098525805 @default.
• W3037578981 cites W3101159255 @default.
• W3037578981 cites W3102147511 @default.
• W3037578981 cites W3103722330 @default.
• W3037578981 cites W3103796865 @default.
• W3037578981 cites W3105128448 @default.
• W3037578981 cites W3105202427 @default.
• W3037578981 cites W3105432754 @default.
• W3037578981 cites W3105627797 @default.
• W3037578981 cites W3105844878 @default.
• W3037578981 cites W4233798822 @default.
• W3037578981 cites W4234284487 @default.
• W3037578981 cites W4244360209 @default.
• W3037578981 cites W4251565392 @default.
• W3037578981 cites W756981418 @default.
• W3037578981 doi "https://doi.org/10.1088/1367-2630/ac4309" @default.
• W3037578981 hasPublicationYear "2022" @default.
• W3037578981 type Work @default.
• W3037578981 sameAs 3037578981 @default.
• W3037578981 citedByCount "5" @default.
• W3037578981 countsByYear W30375789812020 @default.
• W3037578981 countsByYear W30375789812021 @default.
• W3037578981 countsByYear W30375789812022 @default.
• W3037578981 countsByYear W30375789812023 @default.
• W3037578981 crossrefType "journal-article" @default.
• W3037578981 hasAuthorship W3037578981A5024118330 @default.
• W3037578981 hasAuthorship W3037578981A5047565816 @default.
• W3037578981 hasAuthorship W3037578981A5084187489 @default.
• W3037578981 hasBestOaLocation W30375789811 @default.
• W3037578981 hasConcept C118615104 @default.
• W3037578981 hasConcept C119857082 @default.
• W3037578981 hasConcept C121332964 @default.
• W3037578981 hasConcept C126255220 @default.
• W3037578981 hasConcept C154945302 @default.
• W3037578981 hasConcept C18762648 @default.
• W3037578981 hasConcept C2776330181 @default.
• W3037578981 hasConcept C2780069185 @default.
• W3037578981 hasConcept C33923547 @default.
• W3037578981 hasConcept C41008148 @default.
• W3037578981 hasConcept C62520636 @default.
• W3037578981 hasConcept C74859849 @default.

• next