scholarly journals Application of Kohonen's self–organizing feature map algorithm to cortical maps of orientation and direction preference

1998 ◽  
Vol 265 (1398) ◽  
pp. 827-838 ◽  
Author(s):  
N.V. Swindale ◽  
H. Bauer
Keyword(s):  
Cortical Maps ◽  
Feature Map ◽  
Map Algorithm ◽  
Direction Preference ◽  
Self Organizing

Fast self-organizing feature map algorithm

2000 ◽  
Vol 11 (3) ◽  
pp. 721-733 ◽  
Author(s):  
Mu-Chun Su ◽  
Hsiao-Te Chang
Keyword(s):  
Feature Map ◽  
Map Algorithm ◽  
Self Organizing

Speaker recognition using kohonen's self-organizing feature map algorithm

1988 ◽  
Vol 1 ◽  
pp. 311 ◽  
Author(s):  
J. Naylor ◽  
A. Higgins ◽  
K.P. Li ◽  
D. Schmoldt
Keyword(s):  
Speaker Recognition ◽  
Feature Map ◽  
Map Algorithm ◽  
Self Organizing

scholarly journals Architecture neural network deep optimizing based on self organizing feature map algorithm

2020 ◽  
Vol 9 (6) ◽  
pp. 2538-2546
Author(s):  
Muthna Jasim Fadhil ◽  
Majli Nema Hawas ◽  
Maitham Ali Naji
Keyword(s):  
Neural Network ◽  
Feature Map ◽  
Map Algorithm ◽  
Build System ◽  
Error Testing ◽  
Special Algorithm ◽  
Self Organizing

Forward neural network (FNN) execution relying on the algorithm of training and architecture selection. Different parameters using for nip out the architecture of FNN such as the connections number among strata, neurons hidden number in each strata hidden and hidden strata number. Feature architectural combinations exponential could be uncontrollable manually so specific architecture can be design automatically by using special algorithm which build system with ability generalization better. Determination of architecture FNN can be done by using the algorithm of optimization numerous. In this paper methodology new proposes achievement where FNN neurons respective with hidden layers estimation work where in this work collect algorithm training self organizing feature map (SOFM) with advantages to explain how the best architectural selected automatically by SOFM from criteria error testing based on architecture populated. Different size of dataset benchmark of 4 classifications tested for approach proposed.

Sign in / Sign up

Export Citation Format

Share Document