Sciweavers

ML
2006
ACM

Classification-based objective functions

14 years 11 days ago
Classification-based objective functions
Backpropagation, similar to most learning algorithms that can form complex decision surfaces, is prone to overfitting. This work presents classification-based objective functions, an approach to training artificial neural networks on classification problems. Classification-based learning attempts to guide the network directly to correct pattern classification rather than using common error minimization heuristics, such as sum-squared error (SSE) and cross-entropy (CE), that do not explicitly minimize classification error. CB1 is presented here as a novel objective function for learning classification problems. It seeks to directly minimize classification error by backpropagating error only on misclassified patterns from culprit output nodes. CB1 discourages weight saturation and overfitting and achieves higher accuracy on classification problems than optimizing SSE or CE. Experiments on a large OCR data set have shown CB1 to significantly increase generalization accuracy over SSE or CE...
Michael Rimer, Tony Martinez
Added 14 Dec 2010
Updated 14 Dec 2010
Type Journal
Year 2006
Where ML
Authors Michael Rimer, Tony Martinez
Comments (0)