FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W1566320917> ?p ?o ?g. }

• W1566320917 abstract "We have proposed a new information-theoretic approach to competitive learning [1], [2], [3], [4], [5]. The information-theoretic method is a very flexible type of competitive learning, compared with conventional competitive learning. However, some problems have been pointed out concerning the information-theoretic method, for example, slow convergence. In this paper, we propose a new computational method to accelerate a process of information maximization. In addition, an information loss is introduced to detect the salient features of input patterns. Competitive learning is one of the most important techniques in neural networks with many problems such as the dead neuron problem [6], [7]. Thus, many methods have been proposed to solve those problems, for example, conscience learning [8], frequency-sensitive learning [9], rival penalized competitive learning [10], lotto-type competitive learning [11] and entropy maximization [12]. We have so far developed information-theoretic competitive learning to solve those fundamental problems of competitive learning. In the informationtheoretic learning, no dead neurons can be produced, because entropy of competitive units must be maximized. In addition, experimental results have shown that final connection weights are relatively independent of initial conditions. However, one of the major problems is that it is sometimes slow in increasing information. As a problem becomes more complex, heavier computation is needed. Without solving this problem, it is impossible for the information-theoretic method to be applied to practical problems. To overcome this problem, we propose a new type of computational method to accelerate a process of information maximization. In this method, information is supposed to be maximized or sufficiently high at the beginning of learning. This supposed maximum information forces networks to converge to stable points very rapidly. This supposed maximum information is obtained by using the ordinary winner-take-all algorithm. Thus, this method is one in which the winter-takeall is combined with a process of information maximization. We also present a new approach to detect the importance of a given variable, that is, information loss. Information loss is difference between information with all variables and information without a variable, and is used to represent the importance of a given variable. Forced information with information loss can be used to extract main features of input patterns. Connection weights can be interpreted as the main characteristics of classified groups. On the other hand, information loss is used to extract the features on which input O pe n A cc es s D at ab as e w w w .in te ch w eb .o rg" @default.
• W1566320917 created "2016-06-24" @default.
• W1566320917 creator A5079603834 @default.
• W1566320917 date "2009-01-01" @default.
• W1566320917 modified "2023-09-23" @default.
• W1566320917 title "Forced Information for Information-Theoretic Competitive Learning" @default.
• W1566320917 cites W1490454746 @default.
• W1566320917 cites W2011206281 @default.
• W1566320917 cites W2043354238 @default.
• W1566320917 cites W2057973046 @default.
• W1566320917 cites W2069451000 @default.
• W1566320917 cites W2071781501 @default.
• W1566320917 cites W2094015382 @default.
• W1566320917 cites W2159110831 @default.
• W1566320917 cites W2168487341 @default.
• W1566320917 cites W2168993425 @default.
• W1566320917 cites W3023930603 @default.
• W1566320917 doi "https://doi.org/10.5772/6551" @default.
• W1566320917 hasPublicationYear "2009" @default.
• W1566320917 type Work @default.
• W1566320917 sameAs 1566320917 @default.
• W1566320917 citedByCount "0" @default.
• W1566320917 crossrefType "journal-article" @default.
• W1566320917 hasAuthorship W1566320917A5079603834 @default.
• W1566320917 hasConcept C105795698 @default.
• W1566320917 hasConcept C106301342 @default.
• W1566320917 hasConcept C119857082 @default.
• W1566320917 hasConcept C120822770 @default.
• W1566320917 hasConcept C121332964 @default.
• W1566320917 hasConcept C126255220 @default.
• W1566320917 hasConcept C127233936 @default.
• W1566320917 hasConcept C144133560 @default.
• W1566320917 hasConcept C154945302 @default.
• W1566320917 hasConcept C162853370 @default.
• W1566320917 hasConcept C2776330181 @default.
• W1566320917 hasConcept C33923547 @default.
• W1566320917 hasConcept C41008148 @default.
• W1566320917 hasConcept C50644808 @default.
• W1566320917 hasConcept C52622258 @default.
• W1566320917 hasConcept C58546491 @default.
• W1566320917 hasConcept C62520636 @default.
• W1566320917 hasConcept C9679016 @default.
• W1566320917 hasConceptScore W1566320917C105795698 @default.
• W1566320917 hasConceptScore W1566320917C106301342 @default.
• W1566320917 hasConceptScore W1566320917C119857082 @default.
• W1566320917 hasConceptScore W1566320917C120822770 @default.
• W1566320917 hasConceptScore W1566320917C121332964 @default.
• W1566320917 hasConceptScore W1566320917C126255220 @default.
• W1566320917 hasConceptScore W1566320917C127233936 @default.
• W1566320917 hasConceptScore W1566320917C144133560 @default.
• W1566320917 hasConceptScore W1566320917C154945302 @default.
• W1566320917 hasConceptScore W1566320917C162853370 @default.
• W1566320917 hasConceptScore W1566320917C2776330181 @default.
• W1566320917 hasConceptScore W1566320917C33923547 @default.
• W1566320917 hasConceptScore W1566320917C41008148 @default.
• W1566320917 hasConceptScore W1566320917C50644808 @default.
• W1566320917 hasConceptScore W1566320917C52622258 @default.
• W1566320917 hasConceptScore W1566320917C58546491 @default.
• W1566320917 hasConceptScore W1566320917C62520636 @default.
• W1566320917 hasConceptScore W1566320917C9679016 @default.
• W1566320917 hasLocation W15663209171 @default.
• W1566320917 hasOpenAccess W1566320917 @default.
• W1566320917 hasPrimaryLocation W15663209171 @default.
• W1566320917 hasRelatedWork W1505837856 @default.
• W1566320917 hasRelatedWork W1592614963 @default.
• W1566320917 hasRelatedWork W1616330627 @default.
• W1566320917 hasRelatedWork W1975606458 @default.
• W1566320917 hasRelatedWork W203646419 @default.
• W1566320917 hasRelatedWork W2095670500 @default.
• W1566320917 hasRelatedWork W2182277027 @default.
• W1566320917 hasRelatedWork W2182705849 @default.
• W1566320917 hasRelatedWork W2186091528 @default.
• W1566320917 hasRelatedWork W2524689738 @default.
• W1566320917 hasRelatedWork W2544175646 @default.
• W1566320917 hasRelatedWork W2738456714 @default.
• W1566320917 hasRelatedWork W2950476268 @default.
• W1566320917 hasRelatedWork W2996201207 @default.
• W1566320917 hasRelatedWork W3132550281 @default.
• W1566320917 hasRelatedWork W3158006613 @default.
• W1566320917 hasRelatedWork W3201298711 @default.
• W1566320917 hasRelatedWork W3214059887 @default.
• W1566320917 hasRelatedWork W50830905 @default.
• W1566320917 hasRelatedWork W1766837382 @default.
• W1566320917 isParatext "false" @default.
• W1566320917 isRetracted "false" @default.
• W1566320917 magId "1566320917" @default.
• W1566320917 workType "article" @default.