FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2569873096> ?p ?o ?g. }

• W2569873096 endingPage "116" @default.
• W2569873096 startingPage "110" @default.
• W2569873096 abstract "Neural Networks are very successful in acquiring hidden knowledge in datasets. Their most important weakness is that the knowledge they acquired is represented in a form not very understandable to humans. In real life applications understandability of the knowledge acquired by a machine learning system is important. In this thesis, we address the understandability problem of neural networks by converting the knowledge acquired by the neural network into a more understandable form. We do this by extracting a classical decision tree from neural network. We tested the new method on neural networks trained by using real life datasets. We showed that the decision trees extracted have high fidelity to the neural networks they are extracted from. Fidelity measures the closeness of decision tree's outputs to neural network's outputs. We introduced four new splitting techniques to make DecText increase the fidelity of the extracted trees. We showed that the new methods are effective in extracting high fidelity trees. We also introduced a new discretization technique to make DecText be able to handle continuous features. New discretization technique can be used in other induction algorithms if a neural network is trained by using the dataset. We also introduced a new technique to prune the trees extracted. New pruning technique tries to find the simplest tree with the highest fidelity. Another contribution of this thesis is a new feature subset selection technique. Real world classification applications usually have many features. This increases the complexity of the classification task. Choosing a subset of the features may increase accuracy and reduce complexity of the acquired knowledge. We tested the new technique on real world and artificial datasets and compared its results with existing methods. We showed that the new method chooses good subsets by searching fewer states than the existing methods. In the new method, we first sort the features according to their relevance and test the subsets formed by the most relevant features to find a starting subset for searching the subset space. We show that this technique speeds up the search considerably for most of the problem domains." @default.
• W2569873096 created "2017-01-13" @default.
• W2569873096 creator A5005985827 @default.
• W2569873096 creator A5064316755 @default.
• W2569873096 date "2000-01-01" @default.
• W2569873096 modified "2023-09-24" @default.
• W2569873096 title "Converting a trained neural network to a decision tree dectext - decision tree extractor" @default.
• W2569873096 cites W131552660 @default.
• W2569873096 cites W1508395088 @default.
• W2569873096 cites W1547466200 @default.
• W2569873096 cites W1559570474 @default.
• W2569873096 cites W1599216479 @default.
• W2569873096 cites W167515793 @default.
• W2569873096 cites W179133882 @default.
• W2569873096 cites W1969223365 @default.
• W2569873096 cites W1989164753 @default.
• W2569873096 cites W2019363670 @default.
• W2569873096 cites W2048997388 @default.
• W2569873096 cites W2063046703 @default.
• W2569873096 cites W2104873529 @default.
• W2569873096 cites W2113882472 @default.
• W2569873096 cites W2129905273 @default.
• W2569873096 cites W2134682899 @default.
• W2569873096 cites W2605974740 @default.
• W2569873096 cites W53470755 @default.
• W2569873096 hasPublicationYear "2000" @default.
• W2569873096 type Work @default.
• W2569873096 sameAs 2569873096 @default.
• W2569873096 citedByCount "10" @default.
• W2569873096 countsByYear W25698730962012 @default.
• W2569873096 countsByYear W25698730962013 @default.
• W2569873096 countsByYear W25698730962020 @default.
• W2569873096 countsByYear W25698730962021 @default.
• W2569873096 crossrefType "proceedings-article" @default.
• W2569873096 hasAuthorship W2569873096A5005985827 @default.
• W2569873096 hasAuthorship W2569873096A5064316755 @default.
• W2569873096 hasConcept C10229987 @default.
• W2569873096 hasConcept C108010975 @default.
• W2569873096 hasConcept C113174947 @default.
• W2569873096 hasConcept C119857082 @default.
• W2569873096 hasConcept C124101348 @default.
• W2569873096 hasConcept C134306372 @default.
• W2569873096 hasConcept C138885662 @default.
• W2569873096 hasConcept C153180895 @default.
• W2569873096 hasConcept C154945302 @default.
• W2569873096 hasConcept C183931066 @default.
• W2569873096 hasConcept C2776401178 @default.
• W2569873096 hasConcept C2776459999 @default.
• W2569873096 hasConcept C33923547 @default.
• W2569873096 hasConcept C41008148 @default.
• W2569873096 hasConcept C41895202 @default.
• W2569873096 hasConcept C50644808 @default.
• W2569873096 hasConcept C5481197 @default.
• W2569873096 hasConcept C6557445 @default.
• W2569873096 hasConcept C76155785 @default.
• W2569873096 hasConcept C84525736 @default.
• W2569873096 hasConcept C86803240 @default.
• W2569873096 hasConceptScore W2569873096C10229987 @default.
• W2569873096 hasConceptScore W2569873096C108010975 @default.
• W2569873096 hasConceptScore W2569873096C113174947 @default.
• W2569873096 hasConceptScore W2569873096C119857082 @default.
• W2569873096 hasConceptScore W2569873096C124101348 @default.
• W2569873096 hasConceptScore W2569873096C134306372 @default.
• W2569873096 hasConceptScore W2569873096C138885662 @default.
• W2569873096 hasConceptScore W2569873096C153180895 @default.
• W2569873096 hasConceptScore W2569873096C154945302 @default.
• W2569873096 hasConceptScore W2569873096C183931066 @default.
• W2569873096 hasConceptScore W2569873096C2776401178 @default.
• W2569873096 hasConceptScore W2569873096C2776459999 @default.
• W2569873096 hasConceptScore W2569873096C33923547 @default.
• W2569873096 hasConceptScore W2569873096C41008148 @default.
• W2569873096 hasConceptScore W2569873096C41895202 @default.
• W2569873096 hasConceptScore W2569873096C50644808 @default.
• W2569873096 hasConceptScore W2569873096C5481197 @default.
• W2569873096 hasConceptScore W2569873096C6557445 @default.
• W2569873096 hasConceptScore W2569873096C76155785 @default.
• W2569873096 hasConceptScore W2569873096C84525736 @default.
• W2569873096 hasConceptScore W2569873096C86803240 @default.
• W2569873096 hasLocation W25698730961 @default.
• W2569873096 hasOpenAccess W2569873096 @default.
• W2569873096 hasPrimaryLocation W25698730961 @default.
• W2569873096 hasRelatedWork W1489096431 @default.
• W2569873096 hasRelatedWork W1547466200 @default.
• W2569873096 hasRelatedWork W1549490638 @default.
• W2569873096 hasRelatedWork W1594031697 @default.
• W2569873096 hasRelatedWork W1645738616 @default.
• W2569873096 hasRelatedWork W181457951 @default.
• W2569873096 hasRelatedWork W2036547589 @default.
• W2569873096 hasRelatedWork W2063046703 @default.
• W2569873096 hasRelatedWork W2104046064 @default.
• W2569873096 hasRelatedWork W2112649152 @default.
• W2569873096 hasRelatedWork W2113882472 @default.
• W2569873096 hasRelatedWork W2125055259 @default.
• W2569873096 hasRelatedWork W2128971238 @default.
• W2569873096 hasRelatedWork W2134682899 @default.
• W2569873096 hasRelatedWork W2136000097 @default.
• W2569873096 hasRelatedWork W2151523532 @default.
• W2569873096 hasRelatedWork W2158599326 @default.

• next