Presentation 2014-10-16
Image processing by Cellular Neural Networks with Updating Template by Using Reinforcement Learning
Kazushige NATSUNO, Yoko UWATE, Yoshifumi NISHIO,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this study, we proposed Cellular Neural Networks with Updating Template by Using Reinforcement Learning. Performance of CNN depends on template. In addition, the CNN can be varied processing by template. In a general way, the conventional CNN is input varied values. Also, a design of template is spatially and temporal uniform. Therefore, the conventional CNN is restricted to the performance by spatially and temporal uniform template. we proposed space varying CNN with using reinforcement learning by each cell values. In the proposed method, the templates are updated by center and neighboring output values. From some simulation results, we confirm that the proposed CNN is effective for image processing.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Cellular Neural Networks / Reinforcement Learning / Image Processing
Paper # CAS2014-58,NLP2014-52
Date of Issue

Conference Information
Committee CAS
Conference Date 2014/10/9(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Circuits and Systems (CAS)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Image processing by Cellular Neural Networks with Updating Template by Using Reinforcement Learning
Sub Title (in English)
Keyword(1) Cellular Neural Networks
Keyword(2) Reinforcement Learning
Keyword(3) Image Processing
1st Author's Name Kazushige NATSUNO
1st Author's Affiliation Department of Electrical and Electronic Engineering, Tokushima University()
2nd Author's Name Yoko UWATE
2nd Author's Affiliation Department of Electrical and Electronic Engineering, Tokushima University
3rd Author's Name Yoshifumi NISHIO
3rd Author's Affiliation Department of Electrical and Electronic Engineering, Tokushima University
Date 2014-10-16
Paper # CAS2014-58,NLP2014-52
Volume (vol) vol.114
Number (no) 249
Page pp.pp.-
#Pages 4
Date of Issue