FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4282934797> ?p ?o ?g. }

• W4282934797 endingPage "3020" @default.
• W4282934797 startingPage "3007" @default.
• W4282934797 abstract "Feature learning is a promising approach to image classification. However, it is difficult due to high image variations. When the training data are small, it becomes even more challenging, due to the risk of overfitting. Multitask feature learning has shown the potential for improving generalization. However, existing methods are not effective for handling the case that multiple tasks are partially conflicting. Therefore, for the first time, this article proposes to solve a multitask feature learning problem as a multiobjective optimization problem by developing a genetic programming approach with a new representation to image classification. In the new approach, all the tasks share the same solution space and each solution is evaluated on multiple tasks so that the objectives of all the tasks can be optimized simultaneously using a single population. To learn effective features, a new and compact program representation is developed to allow the new approach to evolving solutions shared across tasks. The new approach can automatically find a diverse set of nondominated solutions that achieve good tradeoffs between different tasks. To further reduce the risk of overfitting, an ensemble is created by selecting nondominated solutions to solve each image classification task. The results show that the new approach significantly outperforms a large number of benchmark methods on six problems consisting of 15 image classification datasets of varying difficulty. Further analysis shows that these new designs are effective for improving the performance. The detailed analysis clearly reveals the benefits of solving multitask feature learning as multiobjective optimization in improving the generalization." @default.
• W4282934797 created "2022-06-16" @default.
• W4282934797 creator A5051439492 @default.
• W4282934797 creator A5076701363 @default.
• W4282934797 creator A5077569089 @default.
• W4282934797 date "2023-05-01" @default.
• W4282934797 modified "2023-10-16" @default.
• W4282934797 title "Multitask Feature Learning as Multiobjective Optimization: A New Genetic Programming Approach to Image Classification" @default.
• W4282934797 cites W1722318740 @default.
• W4282934797 cites W2027649639 @default.
• W4282934797 cites W2049583380 @default.
• W4282934797 cites W2103560185 @default.
• W4282934797 cites W2112796928 @default.
• W4282934797 cites W2121238376 @default.
• W4282934797 cites W2125874614 @default.
• W4282934797 cites W2129812935 @default.
• W4282934797 cites W2151103935 @default.
• W4282934797 cites W2155904486 @default.
• W4282934797 cites W2159988601 @default.
• W4282934797 cites W2161969291 @default.
• W4282934797 cites W2163352848 @default.
• W4282934797 cites W2163922914 @default.
• W4282934797 cites W2165097780 @default.
• W4282934797 cites W2167159964 @default.
• W4282934797 cites W2183341477 @default.
• W4282934797 cites W2410677328 @default.
• W4282934797 cites W2413527939 @default.
• W4282934797 cites W2485116416 @default.
• W4282934797 cites W2603025843 @default.
• W4282934797 cites W2883262743 @default.
• W4282934797 cites W2888177567 @default.
• W4282934797 cites W2923639984 @default.
• W4282934797 cites W2928408182 @default.
• W4282934797 cites W2944345944 @default.
• W4282934797 cites W2951774549 @default.
• W4282934797 cites W2964350391 @default.
• W4282934797 cites W2998409228 @default.
• W4282934797 cites W3003566741 @default.
• W4282934797 cites W3016719582 @default.
• W4282934797 cites W3034942609 @default.
• W4282934797 cites W3036020790 @default.
• W4282934797 cites W3094604376 @default.
• W4282934797 cites W3120732119 @default.
• W4282934797 cites W3120969793 @default.
• W4282934797 cites W3156408242 @default.
• W4282934797 cites W3183364302 @default.
• W4282934797 cites W3186891109 @default.
• W4282934797 cites W4237313096 @default.
• W4282934797 doi "https://doi.org/10.1109/tcyb.2022.3174519" @default.
• W4282934797 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/35609102" @default.
• W4282934797 hasPublicationYear "2023" @default.
• W4282934797 type Work @default.
• W4282934797 citedByCount "3" @default.
• W4282934797 countsByYear W42829347972023 @default.
• W4282934797 crossrefType "journal-article" @default.
• W4282934797 hasAuthorship W4282934797A5051439492 @default.
• W4282934797 hasAuthorship W4282934797A5076701363 @default.
• W4282934797 hasAuthorship W4282934797A5077569089 @default.
• W4282934797 hasConcept C110332635 @default.
• W4282934797 hasConcept C115961682 @default.
• W4282934797 hasConcept C119857082 @default.
• W4282934797 hasConcept C127413603 @default.
• W4282934797 hasConcept C13280743 @default.
• W4282934797 hasConcept C134306372 @default.
• W4282934797 hasConcept C138885662 @default.
• W4282934797 hasConcept C153180895 @default.
• W4282934797 hasConcept C154945302 @default.
• W4282934797 hasConcept C177148314 @default.
• W4282934797 hasConcept C177264268 @default.
• W4282934797 hasConcept C17744445 @default.
• W4282934797 hasConcept C185798385 @default.
• W4282934797 hasConcept C199360897 @default.
• W4282934797 hasConcept C199539241 @default.
• W4282934797 hasConcept C201995342 @default.
• W4282934797 hasConcept C205649164 @default.
• W4282934797 hasConcept C22019652 @default.
• W4282934797 hasConcept C2776359362 @default.
• W4282934797 hasConcept C2776401178 @default.
• W4282934797 hasConcept C2780451532 @default.
• W4282934797 hasConcept C28006648 @default.
• W4282934797 hasConcept C33923547 @default.
• W4282934797 hasConcept C41008148 @default.
• W4282934797 hasConcept C41895202 @default.
• W4282934797 hasConcept C45942800 @default.
• W4282934797 hasConcept C50644808 @default.
• W4282934797 hasConcept C59404180 @default.
• W4282934797 hasConcept C68781425 @default.
• W4282934797 hasConcept C75294576 @default.
• W4282934797 hasConcept C94625758 @default.
• W4282934797 hasConceptScore W4282934797C110332635 @default.
• W4282934797 hasConceptScore W4282934797C115961682 @default.
• W4282934797 hasConceptScore W4282934797C119857082 @default.
• W4282934797 hasConceptScore W4282934797C127413603 @default.
• W4282934797 hasConceptScore W4282934797C13280743 @default.
• W4282934797 hasConceptScore W4282934797C134306372 @default.
• W4282934797 hasConceptScore W4282934797C138885662 @default.
• W4282934797 hasConceptScore W4282934797C153180895 @default.
• W4282934797 hasConceptScore W4282934797C154945302 @default.

• next