Title :
Recognition and geometrical on-line learning algorithm of probability distributions
Author_Institution :
Dept. of Phys., Tokyo Inst. of Technol., Japan
Abstract :
An online learning algorithm for probability distributions is constructed in a reparameterization invariant form. It enables us to identify the distributions which transform from one to another by reparameterization. This is an essential property not only for pattern recognition problems but also for the property of `information´. We can find the algorithm to be optimal, since conformal gauge reduces the problem to a noncovariant case
Keywords :
geometry; learning (artificial intelligence); neural nets; online operation; optimisation; pattern recognition; probability; conformal gauge; geometrical online learning algorithm; noncovariant case; optimal algorithm; pattern recognition; probability distributions; reparameterization invariant form; Aerospace engineering; Algorithm design and analysis; Control systems; Educational institutions; Inference algorithms; Learning systems; Pattern recognition; Physics; Probability distribution; Speech processing;
Conference_Titel :
Neural Networks, 2000. IJCNN 2000, Proceedings of the IEEE-INNS-ENNS International Joint Conference on
Conference_Location :
Como
Print_ISBN :
0-7695-0619-4
DOI :
10.1109/IJCNN.2000.861300
