DocumentCode
1908594
Title
Design of an Interval Feed-Forward Neural Network
Author
Srivastava, Sanjeev ; Singh, Monika
Author_Institution
Dept. of Instrum. & Control Eng., Netaji Subhas Inst. of Technol., New Delhi, India
fYear
2012
fDate
5-7 Nov. 2012
Firstpage
211
Lastpage
215
Abstract
Design of new neural networks is restricted due to some problems like stability, plasticity, computational complexity and memory consumption. These problems are overcome in the present work by using an interval feed-forward neural network (IFFNN). It has simple structure that reduces the computational complexity and memory consumption, and the use of Lyapunov stability (LS) based learning algorithm assures the stability. Effectiveness and applicability of the underlying IFFNN model is investigated on benchmark problems of identification.
Keywords
Lyapunov methods; computational complexity; feedforward neural nets; learning (artificial intelligence); plasticity; stability; IFFNN; LS-based learning algorithm; Lyapunov stability based learning algorithm; computational complexity reduction; interval feedforward neural network design; memory consumption reduction; plasticity; Lyapunov stability and identification; Neural network; supervised learning;
fLanguage
English
Publisher
ieee
Conference_Titel
Emerging Trends in Engineering and Technology (ICETET), 2012 Fifth International Conference on
Conference_Location
Himeji
ISSN
2157-0477
Print_ISBN
978-1-4799-0276-7
Type
conf
DOI
10.1109/ICETET.2012.59
Filename
6495248
Link To Document