Summary
the 2014 International Symposium on Nonlinear Theory and its Applications
2014
Session Number:C3L-A
Session:
Number:C3L-A3
A Method of Noise Generation with Cellular Automata for DT-CNN Annealing
Tomohiro FUJITA, Shouta Mizoguchi, Takeshi Kumaki, Takeshi OGURA,
pp.573-576
Publication Date:2014/9/14
Online ISSN:2188-5079
DOI:10.34385/proc.46.C3L-A3
PDF download (323.7KB)
Summary:
A method of random number (noise) generation is proposed. The random number is used for a kind of annealing to achieve global optimization on Discrete Time Cellular Neural Network (DT-CNN). For easy implementation on Cellular Automata (CA) and DT-CNN dedicated hardware engine, Cellular AutoMata on Content Addressable Memory (CAM2), we utilize chaotic behavior of CA to generate noise. The average value of the noises generated by our proposed method is close to 0, and that contributes to improvement of the annealing performance.