Learning Multidimensional Signal Processing
1998 (English)Report (Other academic)
This paper presents our general strategy for designing learning machines as well as a number of particular designs. The search for methods allowing a sufficient level of adaptivity are based on two main principles: 1. Simple adaptive local models and 2. Adaptive model distribution. Particularly important concepts in our work is mutual information and canonical correlation. Examples are given on learning feature descriptors, modeling disparity, synthesis of a global 3-mode model and a setup for reinforcement learning of online video coder parameter control.
Place, publisher, year, edition, pages
Linköping, Sweden: Linköping University, Department of Electrical Engineering , 1998. , 5 p.
LiTH-ISY-R, ISSN 1400-3902 ; 2039
Adaptive model distribution, Simple local models
Databehandling Bildbehandling, Artificiell Intelligens AI
Engineering and Technology
IdentifiersURN: urn:nbn:se:liu:diva-53395ISRN: LITH-ISY-R-2039OAI: oai:DiVA.org:liu-53395DiVA: diva2:288299