Title :
An unsupervised competitive neural network based on local inhibitory links
Author :
Acciani, Giuseppe ; Chiarantoni, Emesto ; Grassi, Giuseppe
Author_Institution :
Dipartimento di Elettrotecnica ed Elettronica, Politecnico di Bari, Italy
Abstract :
This paper describes a new model of unsupervised competitive neural network. The approach, which is based on innovative learning algorithm, exploits local connection among neural units. The aim of the proposed model is to make hardware implementations of competitive neural architectures easier
Keywords :
neural net architecture; unsupervised learning; competitive neural network; local inhibitory links; neural architectures; unsupervised learning; Clocks; Clustering algorithms; Equations; Feature extraction; Neural network hardware; Neural networks; Neurons; Pattern analysis; Pattern recognition; Very large scale integration;
Conference_Titel :
Neural Networks, 2001. Proceedings. IJCNN '01. International Joint Conference on
Conference_Location :
Washington, DC
Print_ISBN :
0-7803-7044-9
DOI :
10.1109/IJCNN.2001.939488
