Matches in SemOpenAlex for { <https://semopenalex.org/work/W3148575653> ?p ?o ?g. }
Showing items 1 to 98 of
98
with 100 items per page.
- W3148575653 endingPage "471" @default.
- W3148575653 startingPage "460" @default.
- W3148575653 abstract "This paper presents a novel Generative Neural Network Architecture for modelling the inverse function of an Artificial Neural Network (ANN) either completely or partially. Modelling the complete inverse function of an ANN involves generating the values of all features that corresponds to a desired output. On the other hand, partially modelling the inverse function means generating the values of a subset of features and fixing the remaining feature values. The feature set generation is a critical step for artificial neural networks, useful in several practical applications in engineering and science. The proposed Oracle Guided Generative Neural Network, dubbed as OGGN, is flexible to handle a variety of feature generation problems. In general, an ANN is able to predict the target values based on given feature vectors. The OGGN architecture enables to generate feature vectors given the predetermined target values of an ANN. When generated feature vectors are fed to the forward ANN, the target value predicted by ANN will be close to the predetermined target values. Therefore, the OGGN architecture is able to map, inverse function of the function represented by forward ANN. Besides, there is another important contribution of this work. This paper also introduces a new class of functions, defined as constraint functions. The constraint functions enable a neural network to investigate a given local space for a longer period of time. Thus, enabling to find a local optimum of the loss function apart from just being able to find the global optimum. OGGN can also be adapted to solve a system of polynomial equations in many variables. The experiments on synthetic datasets validate the effectiveness of OGGN on various use cases. Our code is available at https://github.com/mohammadaaftabv/OGGN ." @default.
- W3148575653 created "2021-04-13" @default.
- W3148575653 creator A5055968340 @default.
- W3148575653 creator A5060979725 @default.
- W3148575653 date "2022-01-01" @default.
- W3148575653 modified "2023-09-27" @default.
- W3148575653 title "OGGN: A Novel Generalized Oracle Guided Generative Architecture for Modelling Inverse Function of Artificial Neural Networks" @default.
- W3148575653 cites W115331676 @default.
- W3148575653 cites W1941659294 @default.
- W3148575653 cites W2014043660 @default.
- W3148575653 cites W2098103715 @default.
- W3148575653 cites W2134961275 @default.
- W3148575653 cites W2137983211 @default.
- W3148575653 cites W2243409905 @default.
- W3148575653 cites W2766162919 @default.
- W3148575653 cites W2807851282 @default.
- W3148575653 cites W2892035503 @default.
- W3148575653 cites W2903564615 @default.
- W3148575653 cites W2909445826 @default.
- W3148575653 cites W2911005554 @default.
- W3148575653 cites W2914274640 @default.
- W3148575653 cites W2949960465 @default.
- W3148575653 cites W2963105487 @default.
- W3148575653 cites W3000404031 @default.
- W3148575653 cites W3002289736 @default.
- W3148575653 cites W3004227146 @default.
- W3148575653 cites W3014980213 @default.
- W3148575653 cites W3021094251 @default.
- W3148575653 cites W3091804884 @default.
- W3148575653 cites W3098900881 @default.
- W3148575653 doi "https://doi.org/10.1007/978-3-031-11349-9_40" @default.
- W3148575653 hasPublicationYear "2022" @default.
- W3148575653 type Work @default.
- W3148575653 sameAs 3148575653 @default.
- W3148575653 citedByCount "0" @default.
- W3148575653 crossrefType "book-chapter" @default.
- W3148575653 hasAuthorship W3148575653A5055968340 @default.
- W3148575653 hasAuthorship W3148575653A5060979725 @default.
- W3148575653 hasBestOaLocation W31485756532 @default.
- W3148575653 hasConcept C115903868 @default.
- W3148575653 hasConcept C138885662 @default.
- W3148575653 hasConcept C14036430 @default.
- W3148575653 hasConcept C140528856 @default.
- W3148575653 hasConcept C154945302 @default.
- W3148575653 hasConcept C175202392 @default.
- W3148575653 hasConcept C207467116 @default.
- W3148575653 hasConcept C2524010 @default.
- W3148575653 hasConcept C2776036281 @default.
- W3148575653 hasConcept C2776401178 @default.
- W3148575653 hasConcept C33923547 @default.
- W3148575653 hasConcept C41008148 @default.
- W3148575653 hasConcept C41895202 @default.
- W3148575653 hasConcept C50644808 @default.
- W3148575653 hasConcept C55166926 @default.
- W3148575653 hasConcept C78458016 @default.
- W3148575653 hasConcept C83665646 @default.
- W3148575653 hasConcept C86582703 @default.
- W3148575653 hasConcept C86803240 @default.
- W3148575653 hasConceptScore W3148575653C115903868 @default.
- W3148575653 hasConceptScore W3148575653C138885662 @default.
- W3148575653 hasConceptScore W3148575653C14036430 @default.
- W3148575653 hasConceptScore W3148575653C140528856 @default.
- W3148575653 hasConceptScore W3148575653C154945302 @default.
- W3148575653 hasConceptScore W3148575653C175202392 @default.
- W3148575653 hasConceptScore W3148575653C207467116 @default.
- W3148575653 hasConceptScore W3148575653C2524010 @default.
- W3148575653 hasConceptScore W3148575653C2776036281 @default.
- W3148575653 hasConceptScore W3148575653C2776401178 @default.
- W3148575653 hasConceptScore W3148575653C33923547 @default.
- W3148575653 hasConceptScore W3148575653C41008148 @default.
- W3148575653 hasConceptScore W3148575653C41895202 @default.
- W3148575653 hasConceptScore W3148575653C50644808 @default.
- W3148575653 hasConceptScore W3148575653C55166926 @default.
- W3148575653 hasConceptScore W3148575653C78458016 @default.
- W3148575653 hasConceptScore W3148575653C83665646 @default.
- W3148575653 hasConceptScore W3148575653C86582703 @default.
- W3148575653 hasConceptScore W3148575653C86803240 @default.
- W3148575653 hasLocation W31485756531 @default.
- W3148575653 hasLocation W31485756532 @default.
- W3148575653 hasLocation W31485756533 @default.
- W3148575653 hasOpenAccess W3148575653 @default.
- W3148575653 hasPrimaryLocation W31485756531 @default.
- W3148575653 hasRelatedWork W1818923569 @default.
- W3148575653 hasRelatedWork W2152280668 @default.
- W3148575653 hasRelatedWork W2354804986 @default.
- W3148575653 hasRelatedWork W2373369388 @default.
- W3148575653 hasRelatedWork W2381052008 @default.
- W3148575653 hasRelatedWork W2386387936 @default.
- W3148575653 hasRelatedWork W2389455353 @default.
- W3148575653 hasRelatedWork W2474469336 @default.
- W3148575653 hasRelatedWork W2779338154 @default.
- W3148575653 hasRelatedWork W3131162510 @default.
- W3148575653 isParatext "false" @default.
- W3148575653 isRetracted "false" @default.
- W3148575653 magId "3148575653" @default.
- W3148575653 workType "book-chapter" @default.