Matches in SemOpenAlex for { <https://semopenalex.org/work/W2417681871> ?p ?o ?g. }
Showing items 1 to 97 of
97
with 100 items per page.
- W2417681871 endingPage "130" @default.
- W2417681871 startingPage "123" @default.
- W2417681871 abstract "We derive a new sequential learning algorithm for Multilayered Perceptron (MLP) neural network robust to outliers. Presence of outliers in data results in failure of the model especially if data processing is performed on-line or in real time. Extended Kalman filter robust to outliers (EKF-OR) is probabilistic generative model in which measurement noise covariance is modeled as stochastic process over the set of symmetric positive-definite matrices in which prior is given as inverse Wishart distribution. Derivation of expressions comes straight form first principles, within Bayesian framework. Analytical intractability of Bayes' update step is solved using Variational Inference (VI). Experimental results obtained using real world stochastic data show that MLP network trained with proposed algorithm achieves low error and average improvement rate of 7% when compared directly to conventional EKF learning algorithm." @default.
- W2417681871 created "2016-06-24" @default.
- W2417681871 creator A5002325220 @default.
- W2417681871 creator A5055641092 @default.
- W2417681871 creator A5078320196 @default.
- W2417681871 date "2015-01-01" @default.
- W2417681871 modified "2023-10-16" @default.
- W2417681871 title "Variational inference for robust sequential learning of multilayered perceptron neural network" @default.
- W2417681871 cites W1590183771 @default.
- W2417681871 cites W1663973292 @default.
- W2417681871 cites W1966252051 @default.
- W2417681871 cites W1977296458 @default.
- W2417681871 cites W1985612626 @default.
- W2417681871 cites W1989358763 @default.
- W2417681871 cites W1990521272 @default.
- W2417681871 cites W2000721204 @default.
- W2417681871 cites W2003699104 @default.
- W2417681871 cites W2033343080 @default.
- W2417681871 cites W2036969206 @default.
- W2417681871 cites W2047950320 @default.
- W2417681871 cites W2055466273 @default.
- W2417681871 cites W2064355448 @default.
- W2417681871 cites W2070871453 @default.
- W2417681871 cites W2088735810 @default.
- W2417681871 cites W2095345875 @default.
- W2417681871 cites W2109455849 @default.
- W2417681871 cites W2112492235 @default.
- W2417681871 cites W2115979064 @default.
- W2417681871 cites W2122146783 @default.
- W2417681871 cites W2128266155 @default.
- W2417681871 cites W2133042373 @default.
- W2417681871 cites W2152907901 @default.
- W2417681871 cites W2301455740 @default.
- W2417681871 cites W2338711590 @default.
- W2417681871 cites W3157049640 @default.
- W2417681871 doi "https://doi.org/10.5937/fmet1502123v" @default.
- W2417681871 hasPublicationYear "2015" @default.
- W2417681871 type Work @default.
- W2417681871 sameAs 2417681871 @default.
- W2417681871 citedByCount "0" @default.
- W2417681871 crossrefType "journal-article" @default.
- W2417681871 hasAuthorship W2417681871A5002325220 @default.
- W2417681871 hasAuthorship W2417681871A5055641092 @default.
- W2417681871 hasAuthorship W2417681871A5078320196 @default.
- W2417681871 hasBestOaLocation W24176818711 @default.
- W2417681871 hasConcept C105795698 @default.
- W2417681871 hasConcept C11413529 @default.
- W2417681871 hasConcept C119857082 @default.
- W2417681871 hasConcept C153180895 @default.
- W2417681871 hasConcept C154945302 @default.
- W2417681871 hasConcept C157286648 @default.
- W2417681871 hasConcept C178650346 @default.
- W2417681871 hasConcept C179717631 @default.
- W2417681871 hasConcept C206833254 @default.
- W2417681871 hasConcept C33923547 @default.
- W2417681871 hasConcept C41008148 @default.
- W2417681871 hasConcept C50644808 @default.
- W2417681871 hasConcept C60908668 @default.
- W2417681871 hasConcept C79337645 @default.
- W2417681871 hasConceptScore W2417681871C105795698 @default.
- W2417681871 hasConceptScore W2417681871C11413529 @default.
- W2417681871 hasConceptScore W2417681871C119857082 @default.
- W2417681871 hasConceptScore W2417681871C153180895 @default.
- W2417681871 hasConceptScore W2417681871C154945302 @default.
- W2417681871 hasConceptScore W2417681871C157286648 @default.
- W2417681871 hasConceptScore W2417681871C178650346 @default.
- W2417681871 hasConceptScore W2417681871C179717631 @default.
- W2417681871 hasConceptScore W2417681871C206833254 @default.
- W2417681871 hasConceptScore W2417681871C33923547 @default.
- W2417681871 hasConceptScore W2417681871C41008148 @default.
- W2417681871 hasConceptScore W2417681871C50644808 @default.
- W2417681871 hasConceptScore W2417681871C60908668 @default.
- W2417681871 hasConceptScore W2417681871C79337645 @default.
- W2417681871 hasFunder F4320322729 @default.
- W2417681871 hasIssue "2" @default.
- W2417681871 hasLocation W24176818711 @default.
- W2417681871 hasLocation W24176818712 @default.
- W2417681871 hasLocation W24176818713 @default.
- W2417681871 hasOpenAccess W2417681871 @default.
- W2417681871 hasPrimaryLocation W24176818711 @default.
- W2417681871 hasRelatedWork W2127064735 @default.
- W2417681871 hasRelatedWork W2338394561 @default.
- W2417681871 hasRelatedWork W3010342546 @default.
- W2417681871 hasRelatedWork W3106494386 @default.
- W2417681871 hasRelatedWork W3185179407 @default.
- W2417681871 hasRelatedWork W4220975826 @default.
- W2417681871 hasRelatedWork W4225307033 @default.
- W2417681871 hasRelatedWork W4231994957 @default.
- W2417681871 hasRelatedWork W4280611221 @default.
- W2417681871 hasRelatedWork W4316082230 @default.
- W2417681871 hasVolume "43" @default.
- W2417681871 isParatext "false" @default.
- W2417681871 isRetracted "false" @default.
- W2417681871 magId "2417681871" @default.
- W2417681871 workType "article" @default.