Minimum Description Length provides a criterion for the selection of models, regardless of their complexity, without the restrictive assumption that the data form a sample from a 'true' distribution.
Extracted from scholarpedia
Source:
Paper: J. Rissanen (1978) Modeling by the shortest data description. Automatica 14, 465-471
Book: P. D. Grünwald (2007) The Minimum Description Length Principle, MIT Press, June 2007, 570 pages
Paper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Multi-Task Learning | 5 | 5.49% |
Multimodal Deep Learning | 4 | 4.40% |
Active Learning | 3 | 3.30% |
Image Classification | 3 | 3.30% |
Reinforcement Learning (RL) | 3 | 3.30% |
Subgroup Discovery | 3 | 3.30% |
General Classification | 3 | 3.30% |
Domain Adaptation | 3 | 3.30% |
Recommendation Systems | 2 | 2.20% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |