Matches in SemOpenAlex for { <https://semopenalex.org/work/W2775821823> ?p ?o ?g. }
Showing items 1 to 76 of
76
with 100 items per page.
- W2775821823 endingPage "466" @default.
- W2775821823 startingPage "444" @default.
- W2775821823 abstract "Abstract Despite various advantages, due to improper training, sometimes a Multi-Layer Perceptron (MLP) classifies a test data point far from the training data into a completely irrelevant class. On the other hand, for example, when we train an MLP to distinguish between four types of childhood cancers (neuroblastoma, rhabdomyosarcoma, non-Hodgkin lymphomas, and Ewing sarcoma) using gene expression profiles and test it on some other kind of cancer (or normal patient) data, the test data will be misclassified to one of the four classes. These unexpected situations arise due to the “open world” nature of the problem. Such problems exist with many other learning systems. We want to address these problems by equipping the network with the ability to not make any judgment when it should not. We have developed an algorithm to provide a practical solution to this problem. We first estimate the domain of the training data (sampling window). We show consistency of our estimate along with some other interesting results. An MLP should say “Don’t know” if a test point is outside the sampling window. To realize this, we generate observations from the complement region and label them to a new class “Don’t know”. We train a network with training data along with the generated data to get a classifier that supports the extra class. The problem of generating a large number of points from the complement region is dealt with a novel scheme that exploits the input sensitivity of the system on the complement region via a regularization. We study the effectiveness of our proposed method with several data sets." @default.
- W2775821823 created "2017-12-22" @default.
- W2775821823 creator A5068185298 @default.
- W2775821823 creator A5082194404 @default.
- W2775821823 date "2018-03-01" @default.
- W2775821823 modified "2023-10-17" @default.
- W2775821823 title "How to make a neural network say “Don’t know”" @default.
- W2775821823 cites W1970088130 @default.
- W2775821823 cites W1977989101 @default.
- W2775821823 cites W1981721425 @default.
- W2775821823 cites W2001619934 @default.
- W2775821823 cites W2009212393 @default.
- W2775821823 cites W2009288137 @default.
- W2775821823 cites W2018459374 @default.
- W2775821823 cites W2027197837 @default.
- W2775821823 cites W2060918050 @default.
- W2775821823 cites W2070084003 @default.
- W2775821823 cites W2072308953 @default.
- W2775821823 cites W2076750860 @default.
- W2775821823 cites W2088538739 @default.
- W2775821823 cites W2092928991 @default.
- W2775821823 cites W2102538225 @default.
- W2775821823 cites W2107808739 @default.
- W2775821823 cites W2114027591 @default.
- W2775821823 cites W2119550927 @default.
- W2775821823 cites W2119880843 @default.
- W2775821823 cites W2132870739 @default.
- W2775821823 cites W2147947791 @default.
- W2775821823 cites W2153158097 @default.
- W2775821823 cites W2162168660 @default.
- W2775821823 cites W2169415433 @default.
- W2775821823 cites W2181203738 @default.
- W2775821823 cites W2962732336 @default.
- W2775821823 doi "https://doi.org/10.1016/j.ins.2017.11.061" @default.
- W2775821823 hasPublicationYear "2018" @default.
- W2775821823 type Work @default.
- W2775821823 sameAs 2775821823 @default.
- W2775821823 citedByCount "13" @default.
- W2775821823 countsByYear W27758218232019 @default.
- W2775821823 countsByYear W27758218232020 @default.
- W2775821823 countsByYear W27758218232021 @default.
- W2775821823 countsByYear W27758218232022 @default.
- W2775821823 countsByYear W27758218232023 @default.
- W2775821823 crossrefType "journal-article" @default.
- W2775821823 hasAuthorship W2775821823A5068185298 @default.
- W2775821823 hasAuthorship W2775821823A5082194404 @default.
- W2775821823 hasConcept C154945302 @default.
- W2775821823 hasConcept C2778519782 @default.
- W2775821823 hasConcept C38652104 @default.
- W2775821823 hasConcept C41008148 @default.
- W2775821823 hasConcept C50644808 @default.
- W2775821823 hasConceptScore W2775821823C154945302 @default.
- W2775821823 hasConceptScore W2775821823C2778519782 @default.
- W2775821823 hasConceptScore W2775821823C38652104 @default.
- W2775821823 hasConceptScore W2775821823C41008148 @default.
- W2775821823 hasConceptScore W2775821823C50644808 @default.
- W2775821823 hasLocation W27758218231 @default.
- W2775821823 hasOpenAccess W2775821823 @default.
- W2775821823 hasPrimaryLocation W27758218231 @default.
- W2775821823 hasRelatedWork W2159443810 @default.
- W2775821823 hasRelatedWork W2325616849 @default.
- W2775821823 hasRelatedWork W2386387936 @default.
- W2775821823 hasRelatedWork W2748952813 @default.
- W2775821823 hasRelatedWork W2899084033 @default.
- W2775821823 hasRelatedWork W3001020386 @default.
- W2775821823 hasRelatedWork W3107474891 @default.
- W2775821823 hasRelatedWork W644753246 @default.
- W2775821823 hasRelatedWork W1629725936 @default.
- W2775821823 hasRelatedWork W2337773048 @default.
- W2775821823 hasVolume "430-431" @default.
- W2775821823 isParatext "false" @default.
- W2775821823 isRetracted "false" @default.
- W2775821823 magId "2775821823" @default.
- W2775821823 workType "article" @default.