Learning multidimensional signal processing
Hans E. Knutsson, Magnus Borga, Tomas Landelius · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · 2002
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.
Cited by 173 works. doi:10.1109/icpr.1998.711968
Authors
References
- A Mathematical Theory of Communication
- A Mathematical Theory of Communication
- Pattern classification and scene analysis
- Adaptation in Natural and Artificial Systems
- Matrix Computations
- Learning representations by back-propagating errors
- Receptive fields, binocular interaction and functional architecture in the cat's visual cortex
- Dynamic Programming
- Neural networks and physical systems with emergent collective computational abilities.
- Neural Networks: A Comprehensive Foundation