Title :
The generalization capabilities of ARTMAP
Author :
Heileman, Gregory L. ; Georgiopoulos, Michael ; Healy, MIichael J. ; Verzi, Stephen J.
Author_Institution :
Dept. of Electr. & Comput. Eng., New Mexico Univ., Albuquerque, NM, USA
Abstract :
Bounds on the number of training examples needed to guarantee a certain level of generalization performance in the ARTMAP architecture are derived. Conditions are derived under which ARTMAP can achieve a specific level of performance assuming any unknown, but fixed, probability distribution on the training data
Keywords :
ART neural nets; generalisation (artificial intelligence); learning (artificial intelligence); neural net architecture; performance evaluation; probability; ART neural nets; ARTMAP; PAC learning; generalization; learning algorithm; neural architecture; probability distribution; Computer architecture; Computer science; Learning systems; Machine learning; Neural networks; Probability distribution; Target tracking; Testing; Training data;
Conference_Titel :
Neural Networks,1997., International Conference on
Conference_Location :
Houston, TX
Print_ISBN :
0-7803-4122-8
DOI :
10.1109/ICNN.1997.616176
