Matches in SemOpenAlex for { <https://semopenalex.org/work/W2894520760> ?p ?o ?g. }
Showing items 1 to 98 of
98
with 100 items per page.
- W2894520760 abstract "The choice of parameters, and the design of the network architecture are important factors affecting the performance of deep neural networks. Genetic Algorithms (GA) have been used before to determine parameters of a network. Yet, GAs perform a finite search over a discrete set of pre-defined candidates, and cannot, in general, generate unseen configurations. In this paper, to move from exploration to exploitation, we propose a novel and systematic method that autonomously and simultaneously optimizes multiple parameters of any deep neural network by using a GA aided by a bi-generative adversarial network (Bi-GAN). The proposed Bi-GAN allows the autonomous exploitation and choice of the number of neurons, for fully-connected layers, and number of filters, for convolutional layers, from a large range of values. Our proposed Bi-GAN involves two generators, and two different models compete and improve each other progressively with a GAN-based strategy to optimize the networks during GA evolution. Our proposed approach can be used to autonomously refine the number of convolutional layers and dense layers, number and size of kernels, and the number of neurons for the dense layers; choose the type of the activation function; and decide whether to use dropout and batch normalization or not, to improve the accuracy of different deep neural network architectures. Without loss of generality, the proposed method has been tested with the ModelNet database, and compared with the 3D Shapenets and two GA-only methods. The results show that the presented approach can simultaneously and successfully optimize multiple neural network parameters, and achieve higher accuracy even with shallower networks." @default.
- W2894520760 created "2018-10-05" @default.
- W2894520760 creator A5004337702 @default.
- W2894520760 creator A5009788938 @default.
- W2894520760 creator A5077680871 @default.
- W2894520760 date "2018-09-24" @default.
- W2894520760 modified "2023-09-27" @default.
- W2894520760 title "Autonomously and Simultaneously Refining Deep Neural Network Parameters by a Bi-Generative Adversarial Network Aided Genetic Algorithm." @default.
- W2894520760 cites W130397803 @default.
- W2894520760 cites W1686810756 @default.
- W2894520760 cites W1799366690 @default.
- W2894520760 cites W1924619199 @default.
- W2894520760 cites W2009969871 @default.
- W2894520760 cites W2108598243 @default.
- W2894520760 cites W2108604074 @default.
- W2894520760 cites W2126105956 @default.
- W2894520760 cites W2173520492 @default.
- W2894520760 cites W2194775991 @default.
- W2894520760 cites W2331128040 @default.
- W2894520760 cites W2508817996 @default.
- W2894520760 cites W2593744649 @default.
- W2894520760 cites W2605287558 @default.
- W2894520760 hasPublicationYear "2018" @default.
- W2894520760 type Work @default.
- W2894520760 sameAs 2894520760 @default.
- W2894520760 citedByCount "2" @default.
- W2894520760 countsByYear W28945207602020 @default.
- W2894520760 crossrefType "posted-content" @default.
- W2894520760 hasAuthorship W2894520760A5004337702 @default.
- W2894520760 hasAuthorship W2894520760A5009788938 @default.
- W2894520760 hasAuthorship W2894520760A5077680871 @default.
- W2894520760 hasConcept C108583219 @default.
- W2894520760 hasConcept C11413529 @default.
- W2894520760 hasConcept C119857082 @default.
- W2894520760 hasConcept C136886441 @default.
- W2894520760 hasConcept C144024400 @default.
- W2894520760 hasConcept C154945302 @default.
- W2894520760 hasConcept C15744967 @default.
- W2894520760 hasConcept C177264268 @default.
- W2894520760 hasConcept C19165224 @default.
- W2894520760 hasConcept C193415008 @default.
- W2894520760 hasConcept C199360897 @default.
- W2894520760 hasConcept C2776145597 @default.
- W2894520760 hasConcept C2780767217 @default.
- W2894520760 hasConcept C2988773926 @default.
- W2894520760 hasConcept C38652104 @default.
- W2894520760 hasConcept C41008148 @default.
- W2894520760 hasConcept C50644808 @default.
- W2894520760 hasConcept C542102704 @default.
- W2894520760 hasConcept C81363708 @default.
- W2894520760 hasConcept C8880873 @default.
- W2894520760 hasConceptScore W2894520760C108583219 @default.
- W2894520760 hasConceptScore W2894520760C11413529 @default.
- W2894520760 hasConceptScore W2894520760C119857082 @default.
- W2894520760 hasConceptScore W2894520760C136886441 @default.
- W2894520760 hasConceptScore W2894520760C144024400 @default.
- W2894520760 hasConceptScore W2894520760C154945302 @default.
- W2894520760 hasConceptScore W2894520760C15744967 @default.
- W2894520760 hasConceptScore W2894520760C177264268 @default.
- W2894520760 hasConceptScore W2894520760C19165224 @default.
- W2894520760 hasConceptScore W2894520760C193415008 @default.
- W2894520760 hasConceptScore W2894520760C199360897 @default.
- W2894520760 hasConceptScore W2894520760C2776145597 @default.
- W2894520760 hasConceptScore W2894520760C2780767217 @default.
- W2894520760 hasConceptScore W2894520760C2988773926 @default.
- W2894520760 hasConceptScore W2894520760C38652104 @default.
- W2894520760 hasConceptScore W2894520760C41008148 @default.
- W2894520760 hasConceptScore W2894520760C50644808 @default.
- W2894520760 hasConceptScore W2894520760C542102704 @default.
- W2894520760 hasConceptScore W2894520760C81363708 @default.
- W2894520760 hasConceptScore W2894520760C8880873 @default.
- W2894520760 hasLocation W28945207601 @default.
- W2894520760 hasOpenAccess W2894520760 @default.
- W2894520760 hasPrimaryLocation W28945207601 @default.
- W2894520760 hasRelatedWork W1527646298 @default.
- W2894520760 hasRelatedWork W2257356363 @default.
- W2894520760 hasRelatedWork W2525340990 @default.
- W2894520760 hasRelatedWork W2762534372 @default.
- W2894520760 hasRelatedWork W2807631648 @default.
- W2894520760 hasRelatedWork W2895839143 @default.
- W2894520760 hasRelatedWork W2898848345 @default.
- W2894520760 hasRelatedWork W2908530716 @default.
- W2894520760 hasRelatedWork W2921245078 @default.
- W2894520760 hasRelatedWork W2948525304 @default.
- W2894520760 hasRelatedWork W2949401153 @default.
- W2894520760 hasRelatedWork W2952645228 @default.
- W2894520760 hasRelatedWork W2967141048 @default.
- W2894520760 hasRelatedWork W3045204521 @default.
- W2894520760 hasRelatedWork W3083123991 @default.
- W2894520760 hasRelatedWork W3093649253 @default.
- W2894520760 hasRelatedWork W3096140875 @default.
- W2894520760 hasRelatedWork W3182611303 @default.
- W2894520760 hasRelatedWork W3214718199 @default.
- W2894520760 hasRelatedWork W2855102660 @default.
- W2894520760 isParatext "false" @default.
- W2894520760 isRetracted "false" @default.
- W2894520760 magId "2894520760" @default.
- W2894520760 workType "article" @default.