Matches in SemOpenAlex for { <https://semopenalex.org/work/W2554281301> ?p ?o ?g. }
Showing items 1 to 95 of
95
with 100 items per page.
- W2554281301 endingPage "118" @default.
- W2554281301 startingPage "111" @default.
- W2554281301 abstract "Echo state networks (ESNs) have become one of the most effective dynamic neural networks because of its excellent fitting performance in real-valued time series modeling tasks and simple training processes. The original ESN concept used randomly fixed created reservoirs, and this concept is considered to be one of its main advantages. However, ESNs have been criticized for its randomly created connectivity and weight parameters. Determining the appropriate weight parameters for a given task is an important problem. An optimization method based on mutual information (MI) is proposed in this study to optimize the input scaling parameters and the structure of ESN to address the aforementioned problem and improve the performance of ESN. The MI optimization method mainly consists of two parts: First, the scaling parameters of multiple inputs are adjusted based on the MI between the network inputs and outputs. Second, some output weight connections are pruned for optimization based on the MI between reservoir states. Furthermore, three MI-ESN models are proposed for a fed-batch penicillin fermentation process. Our experimental outcomes reveal that the obtained MI-ESN models outperform the ESN models without optimization and other traditional neural networks." @default.
- W2554281301 created "2016-11-30" @default.
- W2554281301 creator A5000809799 @default.
- W2554281301 creator A5002453403 @default.
- W2554281301 creator A5083300391 @default.
- W2554281301 date "2017-02-01" @default.
- W2554281301 modified "2023-09-24" @default.
- W2554281301 title "Optimizing the echo state network based on mutual information for modeling fed-batch bioprocesses" @default.
- W2554281301 cites W1487386340 @default.
- W2554281301 cites W1517692491 @default.
- W2554281301 cites W1964709052 @default.
- W2554281301 cites W1976166016 @default.
- W2554281301 cites W2003086804 @default.
- W2554281301 cites W2005874308 @default.
- W2554281301 cites W2011030767 @default.
- W2554281301 cites W2012743186 @default.
- W2554281301 cites W2025291942 @default.
- W2554281301 cites W2029967456 @default.
- W2554281301 cites W2031645826 @default.
- W2554281301 cites W2036202071 @default.
- W2554281301 cites W2036451492 @default.
- W2554281301 cites W2037977515 @default.
- W2554281301 cites W2041645455 @default.
- W2554281301 cites W2043874021 @default.
- W2554281301 cites W2052186154 @default.
- W2554281301 cites W2063378142 @default.
- W2554281301 cites W2063597993 @default.
- W2554281301 cites W2067656095 @default.
- W2554281301 cites W2077854258 @default.
- W2554281301 cites W2084388404 @default.
- W2554281301 cites W2092253051 @default.
- W2554281301 cites W2103442863 @default.
- W2554281301 cites W2109394932 @default.
- W2554281301 cites W2118706537 @default.
- W2554281301 cites W2171865010 @default.
- W2554281301 cites W2200377847 @default.
- W2554281301 cites W2319940424 @default.
- W2554281301 cites W2331298777 @default.
- W2554281301 cites W2332933834 @default.
- W2554281301 doi "https://doi.org/10.1016/j.neucom.2016.11.007" @default.
- W2554281301 hasPublicationYear "2017" @default.
- W2554281301 type Work @default.
- W2554281301 sameAs 2554281301 @default.
- W2554281301 citedByCount "17" @default.
- W2554281301 countsByYear W25542813012018 @default.
- W2554281301 countsByYear W25542813012019 @default.
- W2554281301 countsByYear W25542813012020 @default.
- W2554281301 countsByYear W25542813012021 @default.
- W2554281301 countsByYear W25542813012022 @default.
- W2554281301 crossrefType "journal-article" @default.
- W2554281301 hasAuthorship W2554281301A5000809799 @default.
- W2554281301 hasAuthorship W2554281301A5002453403 @default.
- W2554281301 hasAuthorship W2554281301A5083300391 @default.
- W2554281301 hasConcept C11413529 @default.
- W2554281301 hasConcept C124101348 @default.
- W2554281301 hasConcept C147168706 @default.
- W2554281301 hasConcept C152139883 @default.
- W2554281301 hasConcept C154945302 @default.
- W2554281301 hasConcept C172025690 @default.
- W2554281301 hasConcept C2779426996 @default.
- W2554281301 hasConcept C31258907 @default.
- W2554281301 hasConcept C41008148 @default.
- W2554281301 hasConcept C48103436 @default.
- W2554281301 hasConcept C50644808 @default.
- W2554281301 hasConceptScore W2554281301C11413529 @default.
- W2554281301 hasConceptScore W2554281301C124101348 @default.
- W2554281301 hasConceptScore W2554281301C147168706 @default.
- W2554281301 hasConceptScore W2554281301C152139883 @default.
- W2554281301 hasConceptScore W2554281301C154945302 @default.
- W2554281301 hasConceptScore W2554281301C172025690 @default.
- W2554281301 hasConceptScore W2554281301C2779426996 @default.
- W2554281301 hasConceptScore W2554281301C31258907 @default.
- W2554281301 hasConceptScore W2554281301C41008148 @default.
- W2554281301 hasConceptScore W2554281301C48103436 @default.
- W2554281301 hasConceptScore W2554281301C50644808 @default.
- W2554281301 hasLocation W25542813011 @default.
- W2554281301 hasOpenAccess W2554281301 @default.
- W2554281301 hasPrimaryLocation W25542813011 @default.
- W2554281301 hasRelatedWork W2351280436 @default.
- W2554281301 hasRelatedWork W2511963278 @default.
- W2554281301 hasRelatedWork W2554281301 @default.
- W2554281301 hasRelatedWork W2782083682 @default.
- W2554281301 hasRelatedWork W2788085181 @default.
- W2554281301 hasRelatedWork W2951721681 @default.
- W2554281301 hasRelatedWork W3007634665 @default.
- W2554281301 hasRelatedWork W3107474891 @default.
- W2554281301 hasRelatedWork W3119499520 @default.
- W2554281301 hasRelatedWork W3216623288 @default.
- W2554281301 hasVolume "225" @default.
- W2554281301 isParatext "false" @default.
- W2554281301 isRetracted "false" @default.
- W2554281301 magId "2554281301" @default.
- W2554281301 workType "article" @default.