DocumentCode :
2606770
Title :
Adaptive classification
Author :
Feldkamp, Lee A. ; Feldkamp, Timothy M. ; Prokhorov, Danil V.
Author_Institution :
Res. Lab., Ford Motor Co., Dearborn, MI, USA
fYear :
2000
fDate :
2000
Firstpage :
52
Lastpage :
57
Abstract :
We present an online learning system that is capable of analyzing an input-output data sequence to construct a sequence of binary classifications, without being provided correct class information as part of the training process. The system employs a combination of supervised and unsupervised learning techniques to form two or more behavior models. By examining these models for consistency with the sequence of observed data, an estimate of the class at each time step can be constructed
Keywords :
learning systems; neural nets; pattern classification; unsupervised learning; adaptive classification; behavior models; binary classifications; input-output data sequence; online learning system; supervised learning techniques; unsupervised learning techniques; Current measurement; Data analysis; Fault diagnosis; Information analysis; Laboratories; Learning systems; Neural networks; Noise measurement; Performance evaluation; Time measurement;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Adaptive Systems for Signal Processing, Communications, and Control Symposium 2000. AS-SPCC. The IEEE 2000
Conference_Location :
Lake Louise, Alta.
Print_ISBN :
0-7803-5800-7
Type :
conf
DOI :
10.1109/ASSPCC.2000.882446
Filename :
882446
Link To Document :
بازگشت