Risk-sensitive loss functions for sparse multi-category classification problems
Authors:
- 1 June 2008
- journal article
- Published by Elsevier in Information Sciences
- Vol. 178 (12) , 2621-2638
Abstract
No abstract availableKeywords
This publication has 20 references indexed in Scilit:
- The ‘subsequent artificial neural network’ (SANN) approach might bring more classificatory power to ANN-based DNA microarray analysesBioinformatics, 2004
- Are Loss Functions All the Same?Neural Computation, 2004
- 10.1162/15324430152733133Applied Physics Letters, 2000
- Application of genetic programming for multicategory pattern classificationIEEE Transactions on Evolutionary Computation, 2000
- Cost functions to estimate a posteriori probabilities in multiclass problemsIEEE Transactions on Neural Networks, 1999
- A Decision-Theoretic Generalization of On-Line Learning and an Application to BoostingJournal of Computer and System Sciences, 1997
- A Short Proof of the Posterior Probability Property of Classifier Neural NetworksNeural Computation, 1996
- On loss functions which minimize to conditional expected values and posterior probabilitiesIEEE Transactions on Information Theory, 1993
- Neural Networks and the Bias/Variance DilemmaNeural Computation, 1992
- Neural Network Classifiers Estimate Bayesian a posteriori ProbabilitiesNeural Computation, 1991