FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W1036981403> ?p ?o ?g. }

• W1036981403 endingPage "193" @default.
• W1036981403 startingPage "182" @default.
• W1036981403 abstract "The echo state network (ESN) is a novel and powerful method for the temporal processing of recurrent neural networks. It has tremendous potential for solving a variety of problems, especially real-valued, time-series modeling tasks. However, its complicated topologies and random reservoirs are difficult to implement in practice. For instance, the reservoir must be large enough to capture all data features given that the reservoir is generated randomly. To reduce network complexity and to improve generalization ability, we present a novel optimized ESN (O-ESN) based on binary particle swarm optimization (BPSO). Because the optimization of output weights connection structures is a feature selection problem and PSO has been used as a promising method for feature selection problems, BPSO is employed to determine the optimal connection structures for output weights in the O-ESN. First, we establish and train an ESN with sufficient internal units using training data. The connection structure of output weights, i.e., connection or disconnection, is then optimized through BPSO with validation data. Finally, the performance of the O-ESN is evaluated through test data. This performance is demonstrated in three different types of problems, namely, a system identification and two time-series benchmark tasks. Results show that the O-ESN outperforms the classical feature selection method, least angle regression (LAR) method in that its architecture is simpler than that of LAR." @default.
• W1036981403 created "2016-06-24" @default.
• W1036981403 creator A5000809799 @default.
• W1036981403 creator A5058584802 @default.
• W1036981403 date "2015-09-01" @default.
• W1036981403 modified "2023-10-05" @default.
• W1036981403 title "Optimizing the echo state network with a binary particle swarm optimization algorithm" @default.
• W1036981403 cites W1487386340 @default.
• W1036981403 cites W1488609668 @default.
• W1036981403 cites W1869683314 @default.
• W1036981403 cites W1902688491 @default.
• W1036981403 cites W1959606346 @default.
• W1036981403 cites W1975936518 @default.
• W1036981403 cites W1981630488 @default.
• W1036981403 cites W1985123443 @default.
• W1036981403 cites W1987299193 @default.
• W1036981403 cites W2000621750 @default.
• W1036981403 cites W2001263627 @default.
• W1036981403 cites W2001979953 @default.
• W1036981403 cites W2004900304 @default.
• W1036981403 cites W2012428944 @default.
• W1036981403 cites W2013372804 @default.
• W1036981403 cites W2017538986 @default.
• W1036981403 cites W2024805871 @default.
• W1036981403 cites W2028072219 @default.
• W1036981403 cites W2029897006 @default.
• W1036981403 cites W2029967456 @default.
• W1036981403 cites W2033731173 @default.
• W1036981403 cites W2036451492 @default.
• W1036981403 cites W2038625427 @default.
• W1036981403 cites W2041645455 @default.
• W1036981403 cites W2044371115 @default.
• W1036981403 cites W2046204418 @default.
• W1036981403 cites W2046357518 @default.
• W1036981403 cites W2047844716 @default.
• W1036981403 cites W2048694956 @default.
• W1036981403 cites W2050399271 @default.
• W1036981403 cites W2050546928 @default.
• W1036981403 cites W2061438946 @default.
• W1036981403 cites W2062362073 @default.
• W1036981403 cites W2063396347 @default.
• W1036981403 cites W2063978378 @default.
• W1036981403 cites W2082130524 @default.
• W1036981403 cites W2092038191 @default.
• W1036981403 cites W2094631910 @default.
• W1036981403 cites W2103179919 @default.
• W1036981403 cites W2108028245 @default.
• W1036981403 cites W2108125455 @default.
• W1036981403 cites W2109364787 @default.
• W1036981403 cites W2113368868 @default.
• W1036981403 cites W2114173980 @default.
• W1036981403 cites W2114334669 @default.
• W1036981403 cites W2118706537 @default.
• W1036981403 cites W2121311825 @default.
• W1036981403 cites W2125213524 @default.
• W1036981403 cites W2129324502 @default.
• W1036981403 cites W2131249591 @default.
• W1036981403 cites W2134342468 @default.
• W1036981403 cites W2139287577 @default.
• W1036981403 cites W2140858664 @default.
• W1036981403 cites W2143580736 @default.
• W1036981403 cites W2146174597 @default.
• W1036981403 cites W2147107577 @default.
• W1036981403 cites W2165626886 @default.
• W1036981403 cites W2168015374 @default.
• W1036981403 cites W2169762136 @default.
• W1036981403 cites W2171865010 @default.
• W1036981403 cites W2331298777 @default.
• W1036981403 cites W4234698323 @default.
• W1036981403 cites W4252684946 @default.
• W1036981403 doi "https://doi.org/10.1016/j.knosys.2015.06.003" @default.
• W1036981403 hasPublicationYear "2015" @default.
• W1036981403 type Work @default.
• W1036981403 sameAs 1036981403 @default.
• W1036981403 citedByCount "87" @default.
• W1036981403 countsByYear W10369814032015 @default.
• W1036981403 countsByYear W10369814032016 @default.
• W1036981403 countsByYear W10369814032017 @default.
• W1036981403 countsByYear W10369814032018 @default.
• W1036981403 countsByYear W10369814032019 @default.
• W1036981403 countsByYear W10369814032020 @default.
• W1036981403 countsByYear W10369814032021 @default.
• W1036981403 countsByYear W10369814032022 @default.
• W1036981403 countsByYear W10369814032023 @default.
• W1036981403 crossrefType "journal-article" @default.
• W1036981403 hasAuthorship W1036981403A5000809799 @default.
• W1036981403 hasAuthorship W1036981403A5058584802 @default.
• W1036981403 hasConcept C111919701 @default.
• W1036981403 hasConcept C11413529 @default.
• W1036981403 hasConcept C119857082 @default.
• W1036981403 hasConcept C13280743 @default.
• W1036981403 hasConcept C134306372 @default.
• W1036981403 hasConcept C138885662 @default.
• W1036981403 hasConcept C147168706 @default.
• W1036981403 hasConcept C148483581 @default.
• W1036981403 hasConcept C151406439 @default.
• W1036981403 hasConcept C154945302 @default.
• W1036981403 hasConcept C172025690 @default.

• next