Matches in SemOpenAlex for { <https://semopenalex.org/work/W91463945> ?p ?o ?g. }
Showing items 1 to 67 of
67
with 100 items per page.
- W91463945 endingPage "199" @default.
- W91463945 startingPage "188" @default.
- W91463945 abstract "A crucial problem for connectionist learning schemes is how to partition the space of input vectors into useful categories for subsequent processing. Currently this partitioning is usually accomplished by unsupervised competitive learning algorithms. Although these schemes are simple and fast, they are unable to deal with categorizations that depend on factors other than the vectors' superficial similarity. Specifically they do not take into account feedback (or reinforcement) from outside the system as to the appropriateness of the categorizations that are being learned. We have developed an algorithm and architecture for a connectionist system which mimics unsupervised competitive learning in function; however in form it resembles a reinforcement learning scheme. We call this algorithm competitive reinforcement. This algorithm is inherently more stable than traditional competitive learning paradigms and can be easily and naturally adapted to function in reinforcement learning networks, allowing feature detection to be guided by externally generated reinforcement. A demonstration of the algorithm and its features using the classic dipole stimulus is presented. We suggest that this type of algorithm may be important in the building of large-scale networks for learning complex tasks." @default.
- W91463945 created "2016-06-24" @default.
- W91463945 creator A5035703381 @default.
- W91463945 date "1988-01-01" @default.
- W91463945 modified "2023-09-25" @default.
- W91463945 title "Competitive Reinforcement Learning" @default.
- W91463945 cites W1490454746 @default.
- W91463945 cites W2045466646 @default.
- W91463945 cites W2091565802 @default.
- W91463945 cites W2159110831 @default.
- W91463945 doi "https://doi.org/10.1016/b978-0-934613-64-4.50025-6" @default.
- W91463945 hasPublicationYear "1988" @default.
- W91463945 type Work @default.
- W91463945 sameAs 91463945 @default.
- W91463945 citedByCount "2" @default.
- W91463945 crossrefType "book-chapter" @default.
- W91463945 hasAuthorship W91463945A5035703381 @default.
- W91463945 hasConcept C119857082 @default.
- W91463945 hasConcept C120822770 @default.
- W91463945 hasConcept C127413603 @default.
- W91463945 hasConcept C14036430 @default.
- W91463945 hasConcept C154945302 @default.
- W91463945 hasConcept C199190896 @default.
- W91463945 hasConcept C41008148 @default.
- W91463945 hasConcept C50644808 @default.
- W91463945 hasConcept C66938386 @default.
- W91463945 hasConcept C67203356 @default.
- W91463945 hasConcept C78458016 @default.
- W91463945 hasConcept C8038995 @default.
- W91463945 hasConcept C8521452 @default.
- W91463945 hasConcept C86803240 @default.
- W91463945 hasConcept C97541855 @default.
- W91463945 hasConceptScore W91463945C119857082 @default.
- W91463945 hasConceptScore W91463945C120822770 @default.
- W91463945 hasConceptScore W91463945C127413603 @default.
- W91463945 hasConceptScore W91463945C14036430 @default.
- W91463945 hasConceptScore W91463945C154945302 @default.
- W91463945 hasConceptScore W91463945C199190896 @default.
- W91463945 hasConceptScore W91463945C41008148 @default.
- W91463945 hasConceptScore W91463945C50644808 @default.
- W91463945 hasConceptScore W91463945C66938386 @default.
- W91463945 hasConceptScore W91463945C67203356 @default.
- W91463945 hasConceptScore W91463945C78458016 @default.
- W91463945 hasConceptScore W91463945C8038995 @default.
- W91463945 hasConceptScore W91463945C8521452 @default.
- W91463945 hasConceptScore W91463945C86803240 @default.
- W91463945 hasConceptScore W91463945C97541855 @default.
- W91463945 hasFunder F4320307762 @default.
- W91463945 hasLocation W914639451 @default.
- W91463945 hasOpenAccess W91463945 @default.
- W91463945 hasPrimaryLocation W914639451 @default.
- W91463945 hasRelatedWork W2954428433 @default.
- W91463945 hasRelatedWork W3022038857 @default.
- W91463945 hasRelatedWork W3095538999 @default.
- W91463945 hasRelatedWork W3196155444 @default.
- W91463945 hasRelatedWork W3209574120 @default.
- W91463945 hasRelatedWork W3210156800 @default.
- W91463945 hasRelatedWork W4306321456 @default.
- W91463945 hasRelatedWork W4312812851 @default.
- W91463945 hasRelatedWork W4319083788 @default.
- W91463945 hasRelatedWork W91463945 @default.
- W91463945 isParatext "false" @default.
- W91463945 isRetracted "false" @default.
- W91463945 magId "91463945" @default.
- W91463945 workType "book-chapter" @default.