Matches in SemOpenAlex for { <https://semopenalex.org/work/W2020050961> ?p ?o ?g. }
Showing items 1 to 74 of
74
with 100 items per page.
- W2020050961 endingPage "207" @default.
- W2020050961 startingPage "201" @default.
- W2020050961 abstract "Judd (1988) and Blum and Rivest (1988) have recently proved that the loading problem for neural networks is NP complete. This makes it very unlikely that any algorithm like backpropagation which varies weights on a network of fixed size and topology will be able to learn in polynomial time. However, Valiant has recently proposed a learning protocol (Valiant 1984), which allows one to sensibly consider generalization by learning algorithms with the freedom to add neurons and synapses, as well as simply adjusting weights. Within this context, standard circuit complexity arguments show that learning algorithms with such freedom can solve in polynomial time any learning problem that can be solved in polynomial time by any algorithm whatever. In this sense, neural nets are universal learners, capable of learning any learnable class of concepts." @default.
- W2020050961 created "2016-06-24" @default.
- W2020050961 creator A5059081013 @default.
- W2020050961 date "1989-06-01" @default.
- W2020050961 modified "2023-10-16" @default.
- W2020050961 title "A Proposal for More Powerful Learning Algorithms" @default.
- W2020050961 cites W2008279136 @default.
- W2020050961 cites W2012903341 @default.
- W2020050961 cites W2045717693 @default.
- W2020050961 cites W2091401625 @default.
- W2020050961 cites W2165758113 @default.
- W2020050961 cites W2611147814 @default.
- W2020050961 doi "https://doi.org/10.1162/neco.1989.1.2.201" @default.
- W2020050961 hasPublicationYear "1989" @default.
- W2020050961 type Work @default.
- W2020050961 sameAs 2020050961 @default.
- W2020050961 citedByCount "69" @default.
- W2020050961 countsByYear W20200509612012 @default.
- W2020050961 countsByYear W20200509612014 @default.
- W2020050961 countsByYear W20200509612016 @default.
- W2020050961 countsByYear W20200509612019 @default.
- W2020050961 crossrefType "journal-article" @default.
- W2020050961 hasAuthorship W2020050961A5059081013 @default.
- W2020050961 hasConcept C11413529 @default.
- W2020050961 hasConcept C134306372 @default.
- W2020050961 hasConcept C151730666 @default.
- W2020050961 hasConcept C154945302 @default.
- W2020050961 hasConcept C155032097 @default.
- W2020050961 hasConcept C177148314 @default.
- W2020050961 hasConcept C2777212361 @default.
- W2020050961 hasConcept C2779343474 @default.
- W2020050961 hasConcept C311688 @default.
- W2020050961 hasConcept C33923547 @default.
- W2020050961 hasConcept C41008148 @default.
- W2020050961 hasConcept C50644808 @default.
- W2020050961 hasConcept C80444323 @default.
- W2020050961 hasConcept C86803240 @default.
- W2020050961 hasConcept C90119067 @default.
- W2020050961 hasConceptScore W2020050961C11413529 @default.
- W2020050961 hasConceptScore W2020050961C134306372 @default.
- W2020050961 hasConceptScore W2020050961C151730666 @default.
- W2020050961 hasConceptScore W2020050961C154945302 @default.
- W2020050961 hasConceptScore W2020050961C155032097 @default.
- W2020050961 hasConceptScore W2020050961C177148314 @default.
- W2020050961 hasConceptScore W2020050961C2777212361 @default.
- W2020050961 hasConceptScore W2020050961C2779343474 @default.
- W2020050961 hasConceptScore W2020050961C311688 @default.
- W2020050961 hasConceptScore W2020050961C33923547 @default.
- W2020050961 hasConceptScore W2020050961C41008148 @default.
- W2020050961 hasConceptScore W2020050961C50644808 @default.
- W2020050961 hasConceptScore W2020050961C80444323 @default.
- W2020050961 hasConceptScore W2020050961C86803240 @default.
- W2020050961 hasConceptScore W2020050961C90119067 @default.
- W2020050961 hasIssue "2" @default.
- W2020050961 hasLocation W20200509611 @default.
- W2020050961 hasOpenAccess W2020050961 @default.
- W2020050961 hasPrimaryLocation W20200509611 @default.
- W2020050961 hasRelatedWork W1863534956 @default.
- W2020050961 hasRelatedWork W1868434454 @default.
- W2020050961 hasRelatedWork W1966421350 @default.
- W2020050961 hasRelatedWork W2088845016 @default.
- W2020050961 hasRelatedWork W2128396103 @default.
- W2020050961 hasRelatedWork W4239286941 @default.
- W2020050961 hasRelatedWork W4366984740 @default.
- W2020050961 hasRelatedWork W4366985237 @default.
- W2020050961 hasRelatedWork W4367365565 @default.
- W2020050961 hasRelatedWork W589102260 @default.
- W2020050961 hasVolume "1" @default.
- W2020050961 isParatext "false" @default.
- W2020050961 isRetracted "false" @default.
- W2020050961 magId "2020050961" @default.
- W2020050961 workType "article" @default.