Matches in SemOpenAlex for { <https://semopenalex.org/work/W2000215330> ?p ?o ?g. }
Showing items 1 to 76 of
76
with 100 items per page.
- W2000215330 abstract "We present results that compare the performance of Bayesian learning methods for neural networks on the task of classifying forest scenes into trees and background. Classification task is demanding due to the texture richness of the trees, occlusions of the forest scene objects and diverse lighting conditions under operation. This makes it difficult to determine which are optimal image features for the classification. A natural way to proceed is to extract many different types of potentially suitable features, and to evaluate their usefulness in later processing stages. One approach to cope with large number of features is to use Bayesian methods to control the model complexity. Bayesian learning uses a prior on model parameters, combines this with evidence from a training data, and the integrates over the resulting posterior to make predictions. With this method, we can use large networks and many features without fear of overfitting. For this classification task we compare two Bayesian learning methods for multi-layer perceptron (MLP) neural networks: (1) The evidence framework of MacKay uses a Gaussian approximation to the posterior weight distribution and maximizes with respect to hyperparameters. (2) In a Markov Chain Monte Carlo (MCMC) method due to Neal, the posterior distribution of the network parameters is numerically integrated using the MCMC method. As baseline classifiers for comparison we use (3) MLP early stop committee, (4) K-nearest-neighbor and (5) Classification And Regression Tree." @default.
- W2000215330 created "2016-06-24" @default.
- W2000215330 creator A5007145779 @default.
- W2000215330 creator A5047269552 @default.
- W2000215330 creator A5058539829 @default.
- W2000215330 creator A5087669815 @default.
- W2000215330 date "1998-10-06" @default.
- W2000215330 modified "2023-09-23" @default.
- W2000215330 title "<title>Using Bayesian neural networks to classify forest scenes</title>" @default.
- W2000215330 cites W1554663460 @default.
- W2000215330 cites W1567512734 @default.
- W2000215330 cites W1594031697 @default.
- W2000215330 cites W2059448777 @default.
- W2000215330 cites W2088538739 @default.
- W2000215330 cites W2103384342 @default.
- W2000215330 cites W2111051539 @default.
- W2000215330 cites W591823791 @default.
- W2000215330 cites W113430924 @default.
- W2000215330 doi "https://doi.org/10.1117/12.325800" @default.
- W2000215330 hasPublicationYear "1998" @default.
- W2000215330 type Work @default.
- W2000215330 sameAs 2000215330 @default.
- W2000215330 citedByCount "13" @default.
- W2000215330 countsByYear W20002153302014 @default.
- W2000215330 crossrefType "proceedings-article" @default.
- W2000215330 hasAuthorship W2000215330A5007145779 @default.
- W2000215330 hasAuthorship W2000215330A5047269552 @default.
- W2000215330 hasAuthorship W2000215330A5058539829 @default.
- W2000215330 hasAuthorship W2000215330A5087669815 @default.
- W2000215330 hasConcept C107673813 @default.
- W2000215330 hasConcept C111350023 @default.
- W2000215330 hasConcept C115961682 @default.
- W2000215330 hasConcept C119857082 @default.
- W2000215330 hasConcept C153180895 @default.
- W2000215330 hasConcept C154945302 @default.
- W2000215330 hasConcept C169258074 @default.
- W2000215330 hasConcept C22019652 @default.
- W2000215330 hasConcept C41008148 @default.
- W2000215330 hasConcept C50644808 @default.
- W2000215330 hasConcept C57830394 @default.
- W2000215330 hasConcept C61224824 @default.
- W2000215330 hasConcept C75294576 @default.
- W2000215330 hasConcept C81363708 @default.
- W2000215330 hasConcept C8642999 @default.
- W2000215330 hasConceptScore W2000215330C107673813 @default.
- W2000215330 hasConceptScore W2000215330C111350023 @default.
- W2000215330 hasConceptScore W2000215330C115961682 @default.
- W2000215330 hasConceptScore W2000215330C119857082 @default.
- W2000215330 hasConceptScore W2000215330C153180895 @default.
- W2000215330 hasConceptScore W2000215330C154945302 @default.
- W2000215330 hasConceptScore W2000215330C169258074 @default.
- W2000215330 hasConceptScore W2000215330C22019652 @default.
- W2000215330 hasConceptScore W2000215330C41008148 @default.
- W2000215330 hasConceptScore W2000215330C50644808 @default.
- W2000215330 hasConceptScore W2000215330C57830394 @default.
- W2000215330 hasConceptScore W2000215330C61224824 @default.
- W2000215330 hasConceptScore W2000215330C75294576 @default.
- W2000215330 hasConceptScore W2000215330C81363708 @default.
- W2000215330 hasConceptScore W2000215330C8642999 @default.
- W2000215330 hasLocation W20002153301 @default.
- W2000215330 hasOpenAccess W2000215330 @default.
- W2000215330 hasPrimaryLocation W20002153301 @default.
- W2000215330 hasRelatedWork W2000215330 @default.
- W2000215330 hasRelatedWork W2067114099 @default.
- W2000215330 hasRelatedWork W3012393889 @default.
- W2000215330 hasRelatedWork W3081496756 @default.
- W2000215330 hasRelatedWork W3183325042 @default.
- W2000215330 hasRelatedWork W4210794429 @default.
- W2000215330 hasRelatedWork W4304128395 @default.
- W2000215330 hasRelatedWork W4308353688 @default.
- W2000215330 hasRelatedWork W4309224979 @default.
- W2000215330 hasRelatedWork W4310988130 @default.
- W2000215330 isParatext "false" @default.
- W2000215330 isRetracted "false" @default.
- W2000215330 magId "2000215330" @default.
- W2000215330 workType "article" @default.