Title :
Fast self-organization by query-based algorithm and its applications
Author :
Chang, Ray-I ; Hsiao, Pei-Yung
Author_Institution :
Dept. of Comput. Sci. & Inf. Eng., Nat. Chiao Tung Univ., Hsinchu, Taiwan
Abstract :
A query-based algorithm is introduced to Kohonen´s self-organizing feature maps for finding the best matching neurons with their desire states. It is different from the original self-organization algorithm which finds the best matching neurons with neurons´ current states. The proposed method with a batch view of the self-organization process is a variant of Kohonen´s algorithm. Thus, it can be applied to solve the data clustering problem with pre-specified input vectors. Moreover, the VLSI circuit placement problem without pre-specified input vectors can also be successfully resolved. Comparisons have been made with the original self-organization algorithm, and shown to be better
Keywords :
VLSI; circuit layout; circuit layout CAD; network topology; pattern recognition; self-organising feature maps; Kohonen´s self-organizing feature maps; VLSI circuit placement problem; batch view; current states; data clustering problem; desire state; fast self-organization; matching neurons; prespecified input vectors; query-based algorithm; Application software; Cerebral cortex; Circuits; Clustering algorithms; Data visualization; Humans; Information science; Neural networks; Neurons; Very large scale integration;
Conference_Titel :
Speech, Image Processing and Neural Networks, 1994. Proceedings, ISSIPNN '94., 1994 International Symposium on
Print_ISBN :
0-7803-1865-X
DOI :
10.1109/SIPNN.1994.344959
