scholarly journals Generating neural networks through the induction of threshold logic unit trees

Author(s):  
M. Sahami
2018 ◽  
Vol 13 (1) ◽  
pp. 21-30 ◽  
Author(s):  
A. Medina‐Santiago ◽  
Mario Alfredo Reyes‐Barranca ◽  
Ignacio Algredo‐Badillo ◽  
Alfonso Martinez Cruz ◽  
Kelsey Alejandra Ramírez Gutiérrez ◽  
...  

2008 ◽  
Vol 18 (04) ◽  
pp. 293-303 ◽  
Author(s):  
Y. BÉNÉDIC ◽  
P. WIRA ◽  
J. MERCKLÉ

A new strategy is presented for the implementation of threshold logic functions with binary-output Cellular Neural Networks (CNNs). The objective is to optimize the CNNs weights to develop a robust implementation. Hence, the concept of generative set is introduced as a convenient representation of any linearly separable Boolean function. Our analysis of threshold logic functions leads to a complete algorithm that automatically provides an optimized generative set. New weights are deduced and a more robust CNN template assuming the same function can thus be implemented. The strategy is illustrated by a detailed example.


Sign in / Sign up

Export Citation Format

Share Document