Title :
Error potentials for self-organization
Author :
Heskes, T.M. ; Kappen, Bert
Author_Institution :
Dept. of Med. Phys. & Biophys., Nijmegen Univ., Netherlands
Abstract :
An error potential for self-organizing learning rules is given. The gradient of this error potential leads to the well-known learning rule of Kohonen, except for the determination of the `winning´ unit. The existence of an error potential facilitates a global description of the learning process. A one-dimensional topological map is treated as an example
Keywords :
learning (artificial intelligence); self-organising feature maps; topology; Kohonen learning rules; error potential; global description; learning process; one-dimensional topological map; self-organizing learning rules; winning unit; Biological system modeling; Biophysics; Europe; Information processing; Neural networks; Organizing; Physics; Probability density function; Proposals;
Conference_Titel :
Neural Networks, 1993., IEEE International Conference on
Conference_Location :
San Francisco, CA
Print_ISBN :
0-7803-0999-5
DOI :
10.1109/ICNN.1993.298731
