Computer Science – Computer Vision and Pattern Recognition
Scientific paper
2012-04-01
Computer Science
Computer Vision and Pattern Recognition
Submitted to IEEE Trans. on PAMI
Scientific paper
We propose a robust Fuzzy Stacked Generalization (FSG) technique for deep learning, which assures a better performance than that of the individual classifiers. FSG aggregates a set of fuzzy k- Nearest Neighbor (k-nn) classifiers in a two-level hierarchy. We make a thorough analysis to investigate the learning mechanism of the suggested deep learning architecture and analyze its performance. We suggest two hypotheses to boost the performance of the suggested architec-ture and show that the success of the FSG highly depends on how the individual classifiers share to learn the samples in the training set. Rather than the power of the individual base layer-classifiers, diversity and cooperation of the classifiers become an important issue to improve the overall performance of the proposed FSG. A weak classifier may boost the overall performance more than a strong classifier, if it is capable of recognizing the samples which are not recognized by the rest of the classifiers. Therefore, the problem of designing a deep learning architecture reduces to the design of the feature spaces for the individual classifiers. The experiments explore the type of the collaboration among the individual classifiers, needed for an improved performance of the suggested deep learning architecture.
Ozay Mete
Yarman Vural Fatos T.
No associations
LandOfFree
A New Fuzzy Stacked Generalization Technique for Deep learning and Analysis of its Performance does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with A New Fuzzy Stacked Generalization Technique for Deep learning and Analysis of its Performance, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and A New Fuzzy Stacked Generalization Technique for Deep learning and Analysis of its Performance will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-552361