Soft Computing · 2015 · 31 citations · 16 references
ComputingComputer ScienceArtificial IntelligenceMachine LearningNeural EngineeringError-based LearningLoss FunctionNeural NetworksOptimization For Machine LearningPattern RecognitionRepresentation LearningInstance GenerationMultilayer NetworksMultilayer PerceptronNeural Network ClassificationNoise RobustnessNoise SensitivityPerceptronRobust Loss Functions
In this paper we propose and discuss several new approaches to noise-resistant training of multilayer perceptron neural networks. Two groups of approaches: input ones, based on instance selection and outlier detection, and output ones, based on modified robust error objective functions, are presented and compared. In addition we compare them to some known methods. The experimental evaluation of the methods on classification and regression tasks and comparison of their performances for different amounts of noise in the training data, proves the effectiveness of the proposed approaches.
16
Robust Regression and Outlier Detection
Gregory F. Piepel, Peter J. Rousseeuw, Annick M. Leroy · Technometrics · 1989 · 6.2K citations
Least Median of Squares Regression
Peter J. Rousseeuw · Journal of the American Statistical Association · 1984 · 3.6K citations
UCI Repository of Machine Learning Databases
Christopher J. Merz · Medical Entomology and Zoology · 1996 · 2.3K citations