Matches in SemOpenAlex for { <https://semopenalex.org/work/W205100817> ?p ?o ?g. }
Showing items 1 to 84 of
84
with 100 items per page.
- W205100817 endingPage "11" @default.
- W205100817 startingPage "6" @default.
- W205100817 abstract "Cascade-Correlation is a new architecture and supervised learning algorithm for artificial neural networks and classification techniques. Rather than adjusting the weights in a network of predefined topology, Cascade-Correlation begins with a minimal network and it automatically trains, adds new hidden units one after the other by creating a multi-layer structure. As soon as a new hidden unit has been added to the network, its input-side weights are getting fixed. After that these unit then becomes a permanent feature-identifier in the network, present for producing outputs, then cascadecorrelation is behaves as more complex feature detectors. The Cascade-Correlation networks have several benefits over existing algorithms as it learns very fast. It determines its own size and topology fast. It maintains the structures which it has built even after the training set changes, and it doesn’t need back-propagation of error signals through the connections of the network and its component. Cascade Correlation Neural Network (CCNN) types such as recurrent CCNN, evolving CCNN, genetic CCNN are used to predict software effort from Use Case diagrams in advance manner which helps further for software cost estimation. The use case diagrams are developed in the early stages of the software development and they are used for input. This paper is an overview of cascade-correlation neural networks in which we study different types of cascade-correlation neural network. They are based on a special architecture which autonomously adapts to the application and makes the training much more efficient than the widely used backpropagation algorithm. This review focuses on different types of CCNN and also describes the cascade-correlation architecture variants." @default.
- W205100817 created "2016-06-24" @default.
- W205100817 creator A5004618663 @default.
- W205100817 creator A5081311646 @default.
- W205100817 date "2014-12-22" @default.
- W205100817 modified "2023-09-24" @default.
- W205100817 title "A Review of Cascade Correlation Neural Network for Software Cost Estimation" @default.
- W205100817 cites W1485231155 @default.
- W205100817 cites W1527646298 @default.
- W205100817 cites W1560659665 @default.
- W205100817 cites W1613756701 @default.
- W205100817 cites W1647362478 @default.
- W205100817 cites W1963662492 @default.
- W205100817 cites W1965619387 @default.
- W205100817 cites W1973010432 @default.
- W205100817 cites W1995745802 @default.
- W205100817 cites W2006198120 @default.
- W205100817 cites W2038053785 @default.
- W205100817 cites W2070785919 @default.
- W205100817 cites W2076091918 @default.
- W205100817 cites W2087958197 @default.
- W205100817 cites W2109779438 @default.
- W205100817 cites W2129831132 @default.
- W205100817 cites W2135486589 @default.
- W205100817 cites W2153067348 @default.
- W205100817 cites W2153740650 @default.
- W205100817 cites W2157177276 @default.
- W205100817 cites W2165058188 @default.
- W205100817 cites W2184990502 @default.
- W205100817 cites W2357454289 @default.
- W205100817 cites W2963212551 @default.
- W205100817 cites W3121126077 @default.
- W205100817 cites W3146803896 @default.
- W205100817 hasPublicationYear "2014" @default.
- W205100817 type Work @default.
- W205100817 sameAs 205100817 @default.
- W205100817 citedByCount "0" @default.
- W205100817 crossrefType "journal-article" @default.
- W205100817 hasAuthorship W205100817A5004618663 @default.
- W205100817 hasAuthorship W205100817A5081311646 @default.
- W205100817 hasConcept C119857082 @default.
- W205100817 hasConcept C127413603 @default.
- W205100817 hasConcept C138885662 @default.
- W205100817 hasConcept C153180895 @default.
- W205100817 hasConcept C154945302 @default.
- W205100817 hasConcept C155032097 @default.
- W205100817 hasConcept C175202392 @default.
- W205100817 hasConcept C199360897 @default.
- W205100817 hasConcept C199845137 @default.
- W205100817 hasConcept C2776401178 @default.
- W205100817 hasConcept C2777904410 @default.
- W205100817 hasConcept C31258907 @default.
- W205100817 hasConcept C34146451 @default.
- W205100817 hasConcept C41008148 @default.
- W205100817 hasConcept C41895202 @default.
- W205100817 hasConcept C42360764 @default.
- W205100817 hasConcept C50644808 @default.
- W205100817 hasConceptScore W205100817C119857082 @default.
- W205100817 hasConceptScore W205100817C127413603 @default.
- W205100817 hasConceptScore W205100817C138885662 @default.
- W205100817 hasConceptScore W205100817C153180895 @default.
- W205100817 hasConceptScore W205100817C154945302 @default.
- W205100817 hasConceptScore W205100817C155032097 @default.
- W205100817 hasConceptScore W205100817C175202392 @default.
- W205100817 hasConceptScore W205100817C199360897 @default.
- W205100817 hasConceptScore W205100817C199845137 @default.
- W205100817 hasConceptScore W205100817C2776401178 @default.
- W205100817 hasConceptScore W205100817C2777904410 @default.
- W205100817 hasConceptScore W205100817C31258907 @default.
- W205100817 hasConceptScore W205100817C34146451 @default.
- W205100817 hasConceptScore W205100817C41008148 @default.
- W205100817 hasConceptScore W205100817C41895202 @default.
- W205100817 hasConceptScore W205100817C42360764 @default.
- W205100817 hasConceptScore W205100817C50644808 @default.
- W205100817 hasIssue "2" @default.
- W205100817 hasLocation W2051008171 @default.
- W205100817 hasOpenAccess W205100817 @default.
- W205100817 hasPrimaryLocation W2051008171 @default.
- W205100817 isParatext "false" @default.
- W205100817 isRetracted "false" @default.
- W205100817 magId "205100817" @default.
- W205100817 workType "article" @default.