Matches in SemOpenAlex for { <https://semopenalex.org/work/W66412432> ?p ?o ?g. }
Showing items 1 to 63 of
63
with 100 items per page.
- W66412432 endingPage "16" @default.
- W66412432 startingPage "9" @default.
- W66412432 abstract "In the present study, we demonstrate the learning and recognition capabilities of our recently proposed recurrent neural network (RNN) model called stochastic continuous-time RNN (S-CTRNN). S-CTRNN can learn to predict not only the mean but also the variance of the next state of the learning targets. The network parameters consisting of weights, biases, and initial states of context neurons are optimized through maximum likelihood estimation (MLE) using the gradient descent method. First, we clarify the essential difference between the learning capabilities of conventional CTRNN and S-CTRNN by analyzing the results of a numerical experiment in which multiple fluctuating temporal patterns were used as training data, where the variance of the Gaussian noise varied among the patterns. Furthermore, we also show that the trained S-CTRNN can recognize given fluctuating patterns by inferring the initial states that can reproduce the patterns through the same MLE scheme as that used for network training." @default.
- W66412432 created "2016-06-24" @default.
- W66412432 creator A5000727773 @default.
- W66412432 creator A5021139261 @default.
- W66412432 creator A5038963840 @default.
- W66412432 creator A5055922202 @default.
- W66412432 creator A5065723891 @default.
- W66412432 date "2014-01-01" @default.
- W66412432 modified "2023-09-24" @default.
- W66412432 title "Learning and Recognition of Multiple Fluctuating Temporal Patterns Using S-CTRNN" @default.
- W66412432 cites W196214544 @default.
- W66412432 cites W2020621358 @default.
- W66412432 cites W2025412857 @default.
- W66412432 cites W2028418738 @default.
- W66412432 cites W2068665590 @default.
- W66412432 cites W2071906671 @default.
- W66412432 cites W2079268272 @default.
- W66412432 cites W2083871567 @default.
- W66412432 cites W2110485445 @default.
- W66412432 cites W2147677349 @default.
- W66412432 cites W2184568988 @default.
- W66412432 cites W2766736793 @default.
- W66412432 cites W3207342693 @default.
- W66412432 doi "https://doi.org/10.1007/978-3-319-11179-7_2" @default.
- W66412432 hasPublicationYear "2014" @default.
- W66412432 type Work @default.
- W66412432 sameAs 66412432 @default.
- W66412432 citedByCount "5" @default.
- W66412432 countsByYear W664124322016 @default.
- W66412432 countsByYear W664124322019 @default.
- W66412432 countsByYear W664124322020 @default.
- W66412432 countsByYear W664124322022 @default.
- W66412432 crossrefType "book-chapter" @default.
- W66412432 hasAuthorship W66412432A5000727773 @default.
- W66412432 hasAuthorship W66412432A5021139261 @default.
- W66412432 hasAuthorship W66412432A5038963840 @default.
- W66412432 hasAuthorship W66412432A5055922202 @default.
- W66412432 hasAuthorship W66412432A5065723891 @default.
- W66412432 hasConcept C153180895 @default.
- W66412432 hasConcept C154945302 @default.
- W66412432 hasConcept C41008148 @default.
- W66412432 hasConceptScore W66412432C153180895 @default.
- W66412432 hasConceptScore W66412432C154945302 @default.
- W66412432 hasConceptScore W66412432C41008148 @default.
- W66412432 hasLocation W664124321 @default.
- W66412432 hasOpenAccess W66412432 @default.
- W66412432 hasPrimaryLocation W664124321 @default.
- W66412432 hasRelatedWork W1978450727 @default.
- W66412432 hasRelatedWork W2033914206 @default.
- W66412432 hasRelatedWork W2146076056 @default.
- W66412432 hasRelatedWork W2163831990 @default.
- W66412432 hasRelatedWork W2378160586 @default.
- W66412432 hasRelatedWork W2380927352 @default.
- W66412432 hasRelatedWork W3003836766 @default.
- W66412432 hasRelatedWork W3107474891 @default.
- W66412432 hasRelatedWork W4244943737 @default.
- W66412432 hasRelatedWork W2289108895 @default.
- W66412432 isParatext "false" @default.
- W66412432 isRetracted "false" @default.
- W66412432 magId "66412432" @default.
- W66412432 workType "book-chapter" @default.