FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4294811716> ?p ?o ?g. }

• W4294811716 abstract "The performance of feed-forward neural networks (FFNN) is directly dependant on the training algorithm. Conventional training algorithms such as gradient-based approaches are so popular for FFNN training, but they are susceptible to get stuck in local optimum. To overcome this, population-based metaheuristic algorithms such as differential evolution (DE) are a reliable alternative. In this paper, we propose a novel training algorithm, Reg-IDE, based on an improved DE algorithm. Weight regularisation in conventional algorithms is an approach to reduce the likelihood of over-fitting and enhance generalisation. However, to the best of our knowledge, the current DE-based trainers do not employ regularisation. This paper, first, proposes a regularisation-based objective function to improve the generalisation of the algorithm by adding a new term to the objective function. Then, a region-based strategy determines some regions in search space using a clustering algorithm and updates the population based on the information available in each region. In addition, quasi opposition-based learning enhances the exploration of the algorithm. The best candidate solution found by improved DE is then used as the initial network weights for the Levenberg-Marquardt (LM) algorithm, as a local refinement. Experimental results on different benchmarks and in comparison with 26 conventional and population-based approaches apparently demonstrate the excellent performance of Reg-IDE." @default.
• W4294811716 created "2022-09-06" @default.
• W4294811716 creator A5019996443 @default.
• W4294811716 creator A5028840063 @default.
• W4294811716 creator A5051221811 @default.
• W4294811716 date "2022-07-18" @default.
• W4294811716 modified "2023-09-25" @default.
• W4294811716 title "A Clustering-based Differential Evolution Boosted by a Regularisation-based Objective Function and a Local Refinement for Neural Network Training" @default.
• W4294811716 cites W1490180010 @default.
• W4294811716 cites W1529965533 @default.
• W4294811716 cites W1542136219 @default.
• W4294811716 cites W1595159159 @default.
• W4294811716 cites W1900101064 @default.
• W4294811716 cites W1979695132 @default.
• W4294811716 cites W1982779742 @default.
• W4294811716 cites W1986512036 @default.
• W4294811716 cites W2002302337 @default.
• W4294811716 cites W2006544565 @default.
• W4294811716 cites W2012231377 @default.
• W4294811716 cites W2024555019 @default.
• W4294811716 cites W2032576830 @default.
• W4294811716 cites W2043382734 @default.
• W4294811716 cites W2079143456 @default.
• W4294811716 cites W2083715026 @default.
• W4294811716 cites W2087070363 @default.
• W4294811716 cites W2104352549 @default.
• W4294811716 cites W2107093743 @default.
• W4294811716 cites W2114966295 @default.
• W4294811716 cites W2130372754 @default.
• W4294811716 cites W2137699621 @default.
• W4294811716 cites W2140527568 @default.
• W4294811716 cites W2145178363 @default.
• W4294811716 cites W2157833270 @default.
• W4294811716 cites W2162745921 @default.
• W4294811716 cites W2165299997 @default.
• W4294811716 cites W221059062 @default.
• W4294811716 cites W2232317135 @default.
• W4294811716 cites W2256578114 @default.
• W4294811716 cites W2401135312 @default.
• W4294811716 cites W2553852618 @default.
• W4294811716 cites W2588031254 @default.
• W4294811716 cites W2610544564 @default.
• W4294811716 cites W2745955322 @default.
• W4294811716 cites W2783497650 @default.
• W4294811716 cites W2788871719 @default.
• W4294811716 cites W2810449520 @default.
• W4294811716 cites W2885191712 @default.
• W4294811716 cites W2905396678 @default.
• W4294811716 cites W2944315498 @default.
• W4294811716 cites W2946326863 @default.
• W4294811716 cites W2954434566 @default.
• W4294811716 cites W2957528336 @default.
• W4294811716 cites W2971142824 @default.
• W4294811716 cites W2975160087 @default.
• W4294811716 cites W3099607581 @default.
• W4294811716 cites W3118961950 @default.
• W4294811716 cites W3151089426 @default.
• W4294811716 cites W3158583513 @default.
• W4294811716 cites W3200331528 @default.
• W4294811716 cites W4200565959 @default.
• W4294811716 cites W4220716990 @default.
• W4294811716 cites W4226198731 @default.
• W4294811716 doi "https://doi.org/10.1109/cec55065.2022.9870211" @default.
• W4294811716 hasPublicationYear "2022" @default.
• W4294811716 type Work @default.
• W4294811716 citedByCount "2" @default.
• W4294811716 countsByYear W42948117162023 @default.
• W4294811716 crossrefType "proceedings-article" @default.
• W4294811716 hasAuthorship W4294811716A5019996443 @default.
• W4294811716 hasAuthorship W4294811716A5028840063 @default.
• W4294811716 hasAuthorship W4294811716A5051221811 @default.
• W4294811716 hasConcept C11413529 @default.
• W4294811716 hasConcept C119857082 @default.
• W4294811716 hasConcept C124101348 @default.
• W4294811716 hasConcept C126255220 @default.
• W4294811716 hasConcept C135320971 @default.
• W4294811716 hasConcept C144024400 @default.
• W4294811716 hasConcept C149923435 @default.
• W4294811716 hasConcept C154945302 @default.
• W4294811716 hasConcept C2908647359 @default.
• W4294811716 hasConcept C33923547 @default.
• W4294811716 hasConcept C41008148 @default.
• W4294811716 hasConcept C50644808 @default.
• W4294811716 hasConcept C73555534 @default.
• W4294811716 hasConcept C74750220 @default.
• W4294811716 hasConceptScore W4294811716C11413529 @default.
• W4294811716 hasConceptScore W4294811716C119857082 @default.
• W4294811716 hasConceptScore W4294811716C124101348 @default.
• W4294811716 hasConceptScore W4294811716C126255220 @default.
• W4294811716 hasConceptScore W4294811716C135320971 @default.
• W4294811716 hasConceptScore W4294811716C144024400 @default.
• W4294811716 hasConceptScore W4294811716C149923435 @default.
• W4294811716 hasConceptScore W4294811716C154945302 @default.
• W4294811716 hasConceptScore W4294811716C2908647359 @default.
• W4294811716 hasConceptScore W4294811716C33923547 @default.
• W4294811716 hasConceptScore W4294811716C41008148 @default.
• W4294811716 hasConceptScore W4294811716C50644808 @default.
• W4294811716 hasConceptScore W4294811716C73555534 @default.
• W4294811716 hasConceptScore W4294811716C74750220 @default.
• W4294811716 hasFunder F4320310002 @default.

• next