Matches in SemOpenAlex for { <https://semopenalex.org/work/W1499163862> ?p ?o ?g. }
Showing items 1 to 50 of
50
with 100 items per page.
- W1499163862 abstract "Conventional neural network training methods attempt to find a set of values for the network weights by minimizing an error function using some gradient descent based technique. In order to achieve good generalization performance, it is usually necessary to introduce a regularization term into the error function to prevent weights becoming overly large. In the conventional approach, the regularization coefficient, which controls the degree to which large weights are penalized, must be optimized outside of the weight training procedure, and this is usually done by means of a cross-validation procedure in which some training examples are held out, thereby reducing the number of examples available for weight optimization. Bayesian methods provide a means of optimizing these coefficients within the weight optimization procedure. This paper reports on the application of Bayesian MLP techniques to the task of predicting mineralization potential from geoscientific data. Results demonstrate that the Bayesian approach results in similar maps to the conventional MLP approach, while avoiding the complex cross-validation procedure required by the latter." @default.
- W1499163862 created "2016-06-24" @default.
- W1499163862 creator A5002461826 @default.
- W1499163862 date "2005-01-01" @default.
- W1499163862 modified "2023-09-23" @default.
- W1499163862 title "Automatic MLP Weight Regularization on Mineralization Prediction Tasks" @default.
- W1499163862 cites W2051812123 @default.
- W1499163862 cites W2057591731 @default.
- W1499163862 cites W2110121831 @default.
- W1499163862 cites W2111051539 @default.
- W1499163862 doi "https://doi.org/10.1007/11553939_85" @default.
- W1499163862 hasPublicationYear "2005" @default.
- W1499163862 type Work @default.
- W1499163862 sameAs 1499163862 @default.
- W1499163862 citedByCount "0" @default.
- W1499163862 crossrefType "book-chapter" @default.
- W1499163862 hasAuthorship W1499163862A5002461826 @default.
- W1499163862 hasConcept C107673813 @default.
- W1499163862 hasConcept C11413529 @default.
- W1499163862 hasConcept C119857082 @default.
- W1499163862 hasConcept C153258448 @default.
- W1499163862 hasConcept C154945302 @default.
- W1499163862 hasConcept C2776135515 @default.
- W1499163862 hasConcept C41008148 @default.
- W1499163862 hasConcept C50644808 @default.
- W1499163862 hasConceptScore W1499163862C107673813 @default.
- W1499163862 hasConceptScore W1499163862C11413529 @default.
- W1499163862 hasConceptScore W1499163862C119857082 @default.
- W1499163862 hasConceptScore W1499163862C153258448 @default.
- W1499163862 hasConceptScore W1499163862C154945302 @default.
- W1499163862 hasConceptScore W1499163862C2776135515 @default.
- W1499163862 hasConceptScore W1499163862C41008148 @default.
- W1499163862 hasConceptScore W1499163862C50644808 @default.
- W1499163862 hasLocation W14991638621 @default.
- W1499163862 hasOpenAccess W1499163862 @default.
- W1499163862 hasPrimaryLocation W14991638621 @default.
- W1499163862 hasRelatedWork W2358668433 @default.
- W1499163862 hasRelatedWork W2376932109 @default.
- W1499163862 hasRelatedWork W2390279801 @default.
- W1499163862 hasRelatedWork W2748952813 @default.
- W1499163862 hasRelatedWork W2791939363 @default.
- W1499163862 hasRelatedWork W2899084033 @default.
- W1499163862 hasRelatedWork W2965938919 @default.
- W1499163862 hasRelatedWork W2990311505 @default.
- W1499163862 hasRelatedWork W3107474891 @default.
- W1499163862 hasRelatedWork W3181015691 @default.
- W1499163862 isParatext "false" @default.
- W1499163862 isRetracted "false" @default.
- W1499163862 magId "1499163862" @default.
- W1499163862 workType "book-chapter" @default.