کد مقاله کد نشریه سال انتشار مقاله انگلیسی نسخه تمام متن
6863569 1439515 2018 18 صفحه PDF دانلود رایگان
عنوان انگلیسی مقاله ISI
Building cellular neural network templates with a hardware friendly learning algorithm
ترجمه فارسی عنوان
ساخت مدل شبکه عصبی سلولی با الگوریتم یادگیری سخت افزاری دوستانه
کلمات کلیدی
شبکه عصبی سلولی، قالب های کلونینگ، تغییر وزن تصادفی
موضوعات مرتبط
مهندسی و علوم پایه مهندسی کامپیوتر هوش مصنوعی
چکیده انگلیسی
A general solution for the construction of Cellular Neural Network (CNN) weights (cloning template) with Random Weight Change (RWC) algorithm is proposed. A target image for each input image is prepared via a sketch or any other kind of image processing technique for learning of Cellular Neural Network templates. A vector of randomly generated small values is added to the original weights and tested upon the input-target image pair. As a result, if the learning error decreases, the weight is taken for learning in the next iteration and updated using the same vector of random values. Otherwise, a new random vector for updating the weights is regenerated. One of the strong benefits of the proposed weight learning method is the simplicity of its learning algorithm and hence a simpler hardware architecture. Moreover the proposed method provides a unified solution to the problem of learning CNN templates without having to modify the original CNN structure and is applicable for all types of CNNs and input images. Successful learning of templates for various image processing tasks using different CNN structures are also demonstrated in this paper.
ناشر
Database: Elsevier - ScienceDirect (ساینس دایرکت)
Journal: Neurocomputing - Volume 312, 27 October 2018, Pages 276-284
نویسندگان
, , , ,