Matches in SemOpenAlex for { <https://semopenalex.org/work/W2038884039> ?p ?o ?g. }
Showing items 1 to 72 of
72
with 100 items per page.
- W2038884039 abstract "Recently, the notion that the brain is fundamentally a prediction machine has gained traction within the cognitive science community. Consequently, the ability to learn accurate predictors from experience is crucial to creating intelligent robots. However, in order to make accurate predictions it is necessary to find appropriate data representations from which to learn. Finding such data representations or features is a fundamental challenge for machine learning. Often domain knowledge is employed to design useful features for specific problems, but learning representations in a domain independent manner is highly desirable. While many approaches for automatic feature extraction exist, they are often either computationally expensive or of marginal utility. On the other hand, methods such as Extreme Learning Machines (ELMs) have recently gained popularity as efficient and accurate model learners by employing large collections of fixed, random features. The computational efficiency of these approaches becomes particularly relevant when learning is done fully online, such as is the case for robots learning via their interactions with the world. Selectionist methods, which replace features offering low utility with random replacements, have been shown to produce efficient feature learning in one class of ELM. In this paper we demonstrate that a Darwinian neurodynamic approach of feature replication can improve performance beyond selection alone, and may offer a path towards effective learning of predictive models in robotic agents." @default.
- W2038884039 created "2016-06-24" @default.
- W2038884039 creator A5030271887 @default.
- W2038884039 creator A5059369445 @default.
- W2038884039 creator A5072816120 @default.
- W2038884039 date "2014-07-30" @default.
- W2038884039 modified "2023-10-16" @default.
- W2038884039 title "Online Extreme Evolutionary Learning Machines" @default.
- W2038884039 cites W1494474274 @default.
- W2038884039 cites W1498436455 @default.
- W2038884039 cites W1535810436 @default.
- W2038884039 cites W1538131130 @default.
- W2038884039 cites W1575989700 @default.
- W2038884039 cites W1641311894 @default.
- W2038884039 cites W1968510073 @default.
- W2038884039 cites W1988115241 @default.
- W2038884039 cites W2001685400 @default.
- W2038884039 cites W2026131661 @default.
- W2038884039 cites W2093828424 @default.
- W2038884039 cites W2097861969 @default.
- W2038884039 cites W2100495367 @default.
- W2038884039 cites W2103179919 @default.
- W2038884039 cites W2103496339 @default.
- W2038884039 cites W2105890488 @default.
- W2038884039 cites W2112796928 @default.
- W2038884039 cites W2132424367 @default.
- W2038884039 cites W2147107577 @default.
- W2038884039 cites W2150354929 @default.
- W2038884039 cites W2153791616 @default.
- W2038884039 cites W2260846929 @default.
- W2038884039 cites W2341514930 @default.
- W2038884039 cites W99335134 @default.
- W2038884039 doi "https://doi.org/10.7551/978-0-262-32621-6-ch076" @default.
- W2038884039 hasPublicationYear "2014" @default.
- W2038884039 type Work @default.
- W2038884039 sameAs 2038884039 @default.
- W2038884039 citedByCount "9" @default.
- W2038884039 countsByYear W20388840392015 @default.
- W2038884039 countsByYear W20388840392017 @default.
- W2038884039 countsByYear W20388840392018 @default.
- W2038884039 countsByYear W20388840392019 @default.
- W2038884039 countsByYear W20388840392020 @default.
- W2038884039 countsByYear W20388840392021 @default.
- W2038884039 crossrefType "proceedings-article" @default.
- W2038884039 hasAuthorship W2038884039A5030271887 @default.
- W2038884039 hasAuthorship W2038884039A5059369445 @default.
- W2038884039 hasAuthorship W2038884039A5072816120 @default.
- W2038884039 hasBestOaLocation W20388840392 @default.
- W2038884039 hasConcept C119857082 @default.
- W2038884039 hasConcept C154945302 @default.
- W2038884039 hasConcept C41008148 @default.
- W2038884039 hasConceptScore W2038884039C119857082 @default.
- W2038884039 hasConceptScore W2038884039C154945302 @default.
- W2038884039 hasConceptScore W2038884039C41008148 @default.
- W2038884039 hasLocation W20388840391 @default.
- W2038884039 hasLocation W20388840392 @default.
- W2038884039 hasOpenAccess W2038884039 @default.
- W2038884039 hasPrimaryLocation W20388840391 @default.
- W2038884039 hasRelatedWork W2961085424 @default.
- W2038884039 hasRelatedWork W3046775127 @default.
- W2038884039 hasRelatedWork W3107602296 @default.
- W2038884039 hasRelatedWork W3170094116 @default.
- W2038884039 hasRelatedWork W3209574120 @default.
- W2038884039 hasRelatedWork W4205958290 @default.
- W2038884039 hasRelatedWork W4286629047 @default.
- W2038884039 hasRelatedWork W4306321456 @default.
- W2038884039 hasRelatedWork W4306674287 @default.
- W2038884039 hasRelatedWork W4224009465 @default.
- W2038884039 isParatext "false" @default.
- W2038884039 isRetracted "false" @default.
- W2038884039 magId "2038884039" @default.
- W2038884039 workType "article" @default.