Title :
A new k-groups neural network
Author_Institution :
Dept. of Electron. Eng., Nat. Lien-Ho Inst. of Technol., Miaoli, Taiwan
Abstract :
In this paper, a new neural network model called GROUPSTRON is proposed. Based on a competitive learning algorithm that is originated from the coarse-fine competition, GROUPSTRON can identify the k groups´ elements from a data set. All the elements in the first group are larger than all the elements in the second group and the relation holds for the successive groups. Moreover, simulation results are included to demonstrate the effectiveness of the new network model
Keywords :
neural nets; pattern classification; unsupervised learning; GROUPSTRON; coarse-fine competition; competitive learning algorithm; data set; k-groups neural network; neural network model; Artificial neural networks; Biological neural networks; Electronic mail; Humans; Neural networks; Neurons; Pattern classification; Pattern recognition;
Conference_Titel :
Circuits and Systems, 2000. Proceedings. ISCAS 2000 Geneva. The 2000 IEEE International Symposium on
Conference_Location :
Geneva
Print_ISBN :
0-7803-5482-6
DOI :
10.1109/ISCAS.2000.856146
