Title :
Asymptotical analysis of a modular neural network
Author :
Wang, Lin-Cheng ; Nasrabadi, Nasser M. ; Der, Sandor
Author_Institution :
Dept. of Electr. & Comput. Eng., State Univ. of New York, Buffalo, NY, USA
Abstract :
Modular neural networks have been used in several applications because of their superiority over a single neural network in terms of faster learning, proper data representation, and feasibility of hardware implementation. This paper presents an asymptotical performance analysis showing that the performance of a modular neural network is always better than or as good as that of a single neural network when both neural networks are optimized. The minimum mean square error (MSE) that can be achieved by a modular neural network is also obtained
Keywords :
data structures; learning (artificial intelligence); neural nets; asymptotical performance analysis; data representation; hardware implementation feasibility; learning speed; minimum mean square error; modular neural network; Computer networks; Data engineering; Integrated circuit modeling; Laboratories; Military computing; Milling machines; Neural network hardware; Neural networks; Partitioning algorithms; Powders;
Conference_Titel :
Neural Networks,1997., International Conference on
Conference_Location :
Houston, TX
Print_ISBN :
0-7803-4122-8
DOI :
10.1109/ICNN.1997.616167
