FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2610284419> ?p ?o ?g. }

• W2610284419 abstract "<p>One way to train neural networks is to use evolutionary algorithms such as cooperative coevolution - a method that decomposes the network's learnable parameters into subsets, called subcomponents. Cooperative coevolution gains advantage over other methods by evolving particular subcomponents independently from the rest of the network. Its success depends strongly on how the problem decomposition is carried out. This thesis suggests new forms of problem decomposition, based on a novel and intuitive choice of modularity, and examines in detail at what stage and to what extent the different decomposition methods should be used. The new methods are evaluated by training feedforward networks to solve pattern classification tasks, and by training recurrent networks to solve grammatical inference problems. Efficient problem decomposition methods group interacting variables into the same subcomponents. We examine the methods from the literature and provide an analysis of the nature of the neural network optimization problem in terms of interacting variables. We then present a novel problem decomposition method that groups interacting variables and that can be generalized to neural networks with more than a single hidden layer. We then incorporate local search into cooperative neuro-evolution. We present a memetic cooperative coevolution method that takes into account the cost of employing local search across several sub-populations. The optimisation process changes during evolution in terms of diversity and interacting variables. To address this, we examine the adaptation of the problem decomposition method during the evolutionary process. The results in this thesis show that the proposed methods improve performance in terms of optimization time, scalability and robustness. As a further test, we apply the problem decomposition and adaptive cooperative coevolution methods for training recurrent neural networks on chaotic time series problems. The proposed methods show better performance in terms of accuracy and robustness.</p>" @default.
• W2610284419 created "2017-05-12" @default.
• W2610284419 creator A5043246042 @default.
• W2610284419 date "2021-11-12" @default.
• W2610284419 modified "2023-10-18" @default.
• W2610284419 title "Problem Decomposition and Adaptation in Cooperative Neuro-Evolution" @default.
• W2610284419 cites W120185646 @default.
• W2610284419 cites W1483494099 @default.
• W2610284419 cites W1489651256 @default.
• W2610284419 cites W1491878101 @default.
• W2610284419 cites W1492417045 @default.
• W2610284419 cites W1496915407 @default.
• W2610284419 cites W1497256448 @default.
• W2610284419 cites W1497414364 @default.
• W2610284419 cites W1508379405 @default.
• W2610284419 cites W1514875444 @default.
• W2610284419 cites W1524454772 @default.
• W2610284419 cites W1527420493 @default.
• W2610284419 cites W1539664248 @default.
• W2610284419 cites W1546762028 @default.
• W2610284419 cites W1547737196 @default.
• W2610284419 cites W1549386224 @default.
• W2610284419 cites W1550894544 @default.
• W2610284419 cites W1555689267 @default.
• W2610284419 cites W1558675754 @default.
• W2610284419 cites W1561847687 @default.
• W2610284419 cites W1564372824 @default.
• W2610284419 cites W1565902586 @default.
• W2610284419 cites W1569512666 @default.
• W2610284419 cites W1571424162 @default.
• W2610284419 cites W1591887881 @default.
• W2610284419 cites W1595159159 @default.
• W2610284419 cites W1599736116 @default.
• W2610284419 cites W1604541444 @default.
• W2610284419 cites W1607768087 @default.
• W2610284419 cites W1608919060 @default.
• W2610284419 cites W1644721187 @default.
• W2610284419 cites W169847450 @default.
• W2610284419 cites W1719186128 @default.
• W2610284419 cites W1755390828 @default.
• W2610284419 cites W18216792 @default.
• W2610284419 cites W1917710033 @default.
• W2610284419 cites W1918030494 @default.
• W2610284419 cites W1959983357 @default.
• W2610284419 cites W1964893751 @default.
• W2610284419 cites W1966237354 @default.
• W2610284419 cites W1967429206 @default.
• W2610284419 cites W196871588 @default.
• W2610284419 cites W1969291558 @default.
• W2610284419 cites W1969355111 @default.
• W2610284419 cites W1971464328 @default.
• W2610284419 cites W1982370770 @default.
• W2610284419 cites W1983127429 @default.
• W2610284419 cites W1984205520 @default.
• W2610284419 cites W1987346796 @default.
• W2610284419 cites W1988141348 @default.
• W2610284419 cites W1995341919 @default.
• W2610284419 cites W1996673440 @default.
• W2610284419 cites W1996936486 @default.
• W2610284419 cites W1998937898 @default.
• W2610284419 cites W2000629020 @default.
• W2610284419 cites W2002016471 @default.
• W2610284419 cites W2005369724 @default.
• W2610284419 cites W2005470683 @default.
• W2610284419 cites W2010461070 @default.
• W2610284419 cites W2010659620 @default.
• W2610284419 cites W2011253492 @default.
• W2610284419 cites W2013318791 @default.
• W2610284419 cites W2015265162 @default.
• W2610284419 cites W2015844562 @default.
• W2610284419 cites W2016589492 @default.
• W2610284419 cites W2019207321 @default.
• W2610284419 cites W2019789576 @default.
• W2610284419 cites W2020399841 @default.
• W2610284419 cites W2022710276 @default.
• W2610284419 cites W2024060531 @default.
• W2610284419 cites W2024450772 @default.
• W2610284419 cites W2025987505 @default.
• W2610284419 cites W2027945080 @default.
• W2610284419 cites W2027996967 @default.
• W2610284419 cites W2029807239 @default.
• W2610284419 cites W2030374688 @default.
• W2610284419 cites W2030990735 @default.
• W2610284419 cites W2032507416 @default.
• W2610284419 cites W2036599383 @default.
• W2610284419 cites W2037032215 @default.
• W2610284419 cites W2041724917 @default.
• W2610284419 cites W2046432185 @default.
• W2610284419 cites W2049287437 @default.
• W2610284419 cites W2051848379 @default.
• W2610284419 cites W2053821290 @default.
• W2610284419 cites W2053987251 @default.
• W2610284419 cites W2056364562 @default.
• W2610284419 cites W2056489048 @default.
• W2610284419 cites W2058819127 @default.
• W2610284419 cites W2060123398 @default.
• W2610284419 cites W2062050542 @default.
• W2610284419 cites W2064675550 @default.
• W2610284419 cites W2066251678 @default.
• W2610284419 cites W2068036649 @default.

• next