DocumentCode :
73071
Title :
Fractional Extreme Value Adaptive Training Method: Fractional Steepest Descent Approach
Author :
Yi-Fei Pu ; Ji-Liu Zhou ; Yi Zhang ; Ni Zhang ; Guo Huang ; Siarry, Patrick
Author_Institution :
Sch. of Comput. Sci. & Technol., Sichuan Univ., Chengdu, China
Volume :
26
Issue :
4
fYear :
2015
fDate :
Apr-15
Firstpage :
653
Lastpage :
662
Abstract :
The application of fractional calculus to signal processing and adaptive learning is an emerging area of research. A novel fractional adaptive learning approach that utilizes fractional calculus is presented in this paper. In particular, a fractional steepest descent approach is proposed. A fractional quadratic energy norm is studied, and the stability and convergence of our proposed method are analyzed in detail. The fractional steepest descent approach is implemented numerically and its stability is analyzed experimentally.
Keywords :
gradient methods; signal processing; adaptive learning; fractional calculus; fractional extreme value adaptive training method; fractional quadratic energy norm; fractional steepest descent approach; signal processing; Adaptive control; Convergence; Equations; Fractional calculus; Signal processing algorithms; Training; Fractional calculus; fractional differential; fractional energy norm; fractional extreme point; fractional gradient; fractional gradient.;
fLanguage :
English
Journal_Title :
Neural Networks and Learning Systems, IEEE Transactions on
Publisher :
ieee
ISSN :
2162-237X
Type :
jour
DOI :
10.1109/TNNLS.2013.2286175
Filename :
6650068
Link To Document :
بازگشت