DocumentCode
2047184
Title
The Upper Bound on the Number of Hidden Neurons in Multi-Valued Multi-Threshold Neural Networks
Author
Jiang, Nan ; Zhang, Zhaozhi ; Wang, Jian ; Ma, Xiaomin
Author_Institution
Coll. of Comput., Beijing Univ. of Technol., Beijing
fYear
2009
fDate
23-24 May 2009
Firstpage
1
Lastpage
4
Abstract
By proposing a computational algorithm, this paper gives the upper bound on the number of hidden neurons to realize multi-valued functions defined on N-points. The architecture of the network is three-layer feedforward neural network with one hidden layer. The network is composed of multi-valued multi-threshold neurons. This upper bound can help us to determine the size of network when we design learning algorithms.
Keywords
feedforward neural nets; learning (artificial intelligence); computational algorithm; feedforward neural network; hidden neurons; learning algorithms; multivalued functions; multivalued multithreshold neural networks; multivalued multithreshold neurons; Algorithm design and analysis; Artificial neural networks; Computer architecture; Computer networks; Educational institutions; Feedforward neural networks; Neural networks; Neurons; Physics computing; Upper bound;
fLanguage
English
Publisher
ieee
Conference_Titel
Intelligent Systems and Applications, 2009. ISA 2009. International Workshop on
Conference_Location
Wuhan
Print_ISBN
978-1-4244-3893-8
Electronic_ISBN
978-1-4244-3894-5
Type
conf
DOI
10.1109/IWISA.2009.5073217
Filename
5073217
Link To Document