Matches in SemOpenAlex for { <https://semopenalex.org/work/W2472674908> ?p ?o ?g. }
Showing items 1 to 67 of
67
with 100 items per page.
- W2472674908 abstract "A recurrent neural network is a one-layer network with lateral-connection. It feedbacks the output vector to the input during processing and stops when the output vector is stable. A recurrent neural network can act as an associative memory, and the capacity is an important criterion in this kind of memory. Therefore, the study of the capacity of recurrent neural network attracted many researchers.In our study of the capacity of recurrent neural networks, we find an upper bound of the network, which is a function of r, the minimum attraction radius of all attraction regions. Many works focused on the topic of the capacity of recurrent neural network. However, there is a big gap between the capacity of those works and the upper bound.In this dissertation, we propose a High Capacity (HC) model which explores the capacity, $${nchoose lfloor{nover2}rfloor},$$of recurrent neural network. It is the high capacity. The HC model reduces the benefit of noise tolerance to obtain a high capacity. We analyze the properties resulted from the proposed model.The comparisons of the proposed model with other works are discussed in terms of the number of capacity and the behavior of the network. We also discuss several methods regarding the intersection and subtraction of two HC models.Hopfield neural network is one of the most widely studied model among the recurrent neural networks. We propose an efficient simulation model for Hopfield neural networks based on the condition that the number of memorized vectors, m, is smaller than the number of neurons, n, in the network." @default.
- W2472674908 created "2016-07-22" @default.
- W2472674908 creator A5034825040 @default.
- W2472674908 date "1993-01-11" @default.
- W2472674908 modified "2023-09-26" @default.
- W2472674908 title "A model of recurrent neural network with high capacity" @default.
- W2472674908 hasPublicationYear "1993" @default.
- W2472674908 type Work @default.
- W2472674908 sameAs 2472674908 @default.
- W2472674908 citedByCount "1" @default.
- W2472674908 crossrefType "journal-article" @default.
- W2472674908 hasAuthorship W2472674908A5034825040 @default.
- W2472674908 hasConcept C120620853 @default.
- W2472674908 hasConcept C134306372 @default.
- W2472674908 hasConcept C147168706 @default.
- W2472674908 hasConcept C149635348 @default.
- W2472674908 hasConcept C154945302 @default.
- W2472674908 hasConcept C175202392 @default.
- W2472674908 hasConcept C177973122 @default.
- W2472674908 hasConcept C2780513914 @default.
- W2472674908 hasConcept C33923547 @default.
- W2472674908 hasConcept C41008148 @default.
- W2472674908 hasConcept C46421273 @default.
- W2472674908 hasConcept C50644808 @default.
- W2472674908 hasConcept C53442348 @default.
- W2472674908 hasConcept C77553402 @default.
- W2472674908 hasConceptScore W2472674908C120620853 @default.
- W2472674908 hasConceptScore W2472674908C134306372 @default.
- W2472674908 hasConceptScore W2472674908C147168706 @default.
- W2472674908 hasConceptScore W2472674908C149635348 @default.
- W2472674908 hasConceptScore W2472674908C154945302 @default.
- W2472674908 hasConceptScore W2472674908C175202392 @default.
- W2472674908 hasConceptScore W2472674908C177973122 @default.
- W2472674908 hasConceptScore W2472674908C2780513914 @default.
- W2472674908 hasConceptScore W2472674908C33923547 @default.
- W2472674908 hasConceptScore W2472674908C41008148 @default.
- W2472674908 hasConceptScore W2472674908C46421273 @default.
- W2472674908 hasConceptScore W2472674908C50644808 @default.
- W2472674908 hasConceptScore W2472674908C53442348 @default.
- W2472674908 hasConceptScore W2472674908C77553402 @default.
- W2472674908 hasLocation W24726749081 @default.
- W2472674908 hasOpenAccess W2472674908 @default.
- W2472674908 hasPrimaryLocation W24726749081 @default.
- W2472674908 hasRelatedWork W1004474716 @default.
- W2472674908 hasRelatedWork W1591693031 @default.
- W2472674908 hasRelatedWork W2031614634 @default.
- W2472674908 hasRelatedWork W2082414270 @default.
- W2472674908 hasRelatedWork W2171673774 @default.
- W2472674908 hasRelatedWork W2305874582 @default.
- W2472674908 hasRelatedWork W2437268865 @default.
- W2472674908 hasRelatedWork W2488966382 @default.
- W2472674908 hasRelatedWork W2767038835 @default.
- W2472674908 hasRelatedWork W2775748041 @default.
- W2472674908 hasRelatedWork W2801147603 @default.
- W2472674908 hasRelatedWork W2888261300 @default.
- W2472674908 hasRelatedWork W2895785242 @default.
- W2472674908 hasRelatedWork W2901734170 @default.
- W2472674908 hasRelatedWork W2962715412 @default.
- W2472674908 hasRelatedWork W2964265541 @default.
- W2472674908 hasRelatedWork W3099671139 @default.
- W2472674908 hasRelatedWork W348507692 @default.
- W2472674908 hasRelatedWork W6336603 @default.
- W2472674908 hasRelatedWork W67028414 @default.
- W2472674908 isParatext "false" @default.
- W2472674908 isRetracted "false" @default.
- W2472674908 magId "2472674908" @default.
- W2472674908 workType "article" @default.