DocumentCode :
2954453
Title :
Analysis of nonseparable property of multi-valued multi-threshold neuron
Author :
Jiang, Nan ; Zhang, Zhaozhi ; Ma, Xiaomin ; Wang, Jian ; Yang, Yixian
Author_Institution :
Coll. of Comput. Sci. & Technol., Beijing Univ. of Technol., Beijing
fYear :
2008
fDate :
1-8 June 2008
Firstpage :
413
Lastpage :
419
Abstract :
We consider the multi-valued discrete real training set that can not be separated by one multi-valued multi-threshold neuron. Such training set is defined as linearly nonseparable set in this paper. Our objective is to use multi-valued multi-threshold neural networks to learn nonseparable training sets. First we give the method that how to determine a training set is separable or nonseparable (i.e., the necessary and sufficient condition for linearly nonseparable is given). Then we analyze the structures within linearly nonseparable sets: not all the vectors in a linearly nonseparable set are responsible for nonseparability. So the vectors in such set can be partitioned to separable vectors and nonseparable vectors. Finally, we discuss the learning problems for a linearly nonseparable set. Such set can be learned by a three-layer feedforward neural network with one hidden layer. An example throughout the paper further clarifies the results of this paper.
Keywords :
feedforward neural nets; learning (artificial intelligence); set theory; vectors; multivalued discrete real training set; multivalued multi threshold neural network; nonseparable training set learning; nonseparable vector; three-layer feedforward neural network; Neural networks; Neurons;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Neural Networks, 2008. IJCNN 2008. (IEEE World Congress on Computational Intelligence). IEEE International Joint Conference on
Conference_Location :
Hong Kong
ISSN :
1098-7576
Print_ISBN :
978-1-4244-1820-6
Electronic_ISBN :
1098-7576
Type :
conf
DOI :
10.1109/IJCNN.2008.4633825
Filename :
4633825
Link To Document :
بازگشت