Philosophical Issues in Kolmogorov Complexity
ICALP '92 Proceedings of the 19th International Colloquium on Automata, Languages and Programming
MDL-Based Selection of the Number of Components in Mixture Models for Pattern Classification
SSPR '98/SPR '98 Proceedings of the Joint IAPR International Workshops on Advances in Pattern Recognition
A Compression Approach to Support Vector Model Selection
The Journal of Machine Learning Research
Vision: A Computational Investigation into the Human Representation and Processing of Visual Information
Hi-index | 0.00 |
Problems of decision criteria in tasks of image analysis and pattern recognition are considered. Overlearning as a practical consequence of fundamental paradoxes in inductive inference is illustrated by examples. Theoretical (based on algorithmic complexity) and practical formulations of the minimum description length (MDL) principle are given. A decrease in the overlearning effect is shown on examples of modern recognition, grouping, and segmentation methods modified by the MDL principle. The representational MDL principle is introduced as an extension of the MDL principle, which makes it possible to take into account the dependence of the optimality criterion of the model from prior information given in data representation, as well as to perform optimization of representations. Novel possibilities of constructing learnable image analysis algorithms by optimizing the representation based on the extended MDL principle are described.