.png){kind=icon}
返回
Building cellular neural network templates with a hardware friendly learning algorithm
.png){kind=icon}
OA
AI
DOI：10.1016/j.neucom.2018.05.113.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
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. (C) 2018 Elsevier B.V. All rights reserved.
Keyword:
Cellular neural network
Cloning templates
Random weight change
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
6.5
论文数:
2.5W
被引数:
6.5W
机构
引用论文
A Circuit-Based Learning Architecture for Multilayer Neural Networks With Memristor Bridge Synapses
.png){kind=icon}
PREAI
分享收藏分享收藏Model Predictive Control for Tracking of Underactuated Vessels Based on Recurrent Neural Networks基于递归神经网络的欠驱动船舶跟踪模型预测控制
PREAI
分享收藏
查看更多内容