Title :
A neural architecture for hierarchical clustering
Author :
Bouzerdoum, A. ; Southcott, M.L. ; Zhu, J. ; Bogner, R.E.
Author_Institution :
Dept. of Electr. & Electron. Eng., Adelaide Univ., SA, Australia
Abstract :
An hierarchical neural network structure for clustering problems is presented and a statistical analysis of its performance is conducted. This neural network architecture aims to find, through competition and cooperation, maximally related objects in a scene. The architecture was first introduced by Maren and Ali (1983), and was named the hierarchical scene structure (HSS). We propose an enhancement of the original HSS and demonstrate that this leads to an improved performance. It is also shown that further improvement in performance can be achieved by cascading two enhanced HSS networks
Keywords :
feedforward neural nets; image segmentation; multilayer perceptrons; neural net architecture; statistical analysis; unsupervised learning; competition; cooperation; hierarchical clustering; hierarchical neural network architecture; hierarchical scene structure; image segments clustering; maximally related objects; multilayered cooperative competitive neural network; performance; statistical analysis; Computer architecture; Image segmentation; Information processing; Layout; Multi-layer neural network; Neural networks; Neurons; Radar tracking; Signal processing; Statistical analysis;
Conference_Titel :
Acoustics, Speech, and Signal Processing, 1994. ICASSP-94., 1994 IEEE International Conference on
Conference_Location :
Adelaide, SA
Print_ISBN :
0-7803-1775-0
DOI :
10.1109/ICASSP.1994.389569
