ID	原文	译文
56568	通过大量实验仿真可以看出,在预知系统拓扑的前提下,可以显著地减少通过交换机的流量,进而缩短修盘的时间.	The results of simulationexperiments demonstrate that the repair time is improved significantly and repair traffic is reduced notably.
56569	细胞神经网络(cellular neural network, CNN)具有简单的局部互联结构和高速并行处理能力,是构造人工视网膜的基础模型,可被应用于机器视觉中图像处理时的图像增强等方面.	Cellular neural networks (CNN) have a simple local interconnect structure and high-speed parallelprocessing capability. As the basic model for a constructing artificial retina, CNNs can be applied to imageenhancement in the machine vision field. However, existing image enhancement methods based on CNNs faceseveral challenges.
56570	然而,现有的此类图像增强方法尚存在一些不足,例如,在处理实际复杂图像时,采用固定模板难以取得理想效果;	For example, when using common fixed templates, it is difficult to obtain ideal results whenhandling complex images in real-world applications.
56571	而且,未能模拟人类视觉系统的全局和局部自适应调节特性,缺乏仿生考虑.	In addition, the lack of bionic considerations can cause failureswhen simulating the powerful global and local adaptive adjustment characteristics of human vision.
56572	因此,本文融合自适应三高斯(tri-Gaussian)理论和纳米信息器件忆阻器,提出了一种用于图像增强的新型仿生自适应忆阻细胞神经网络.	Therefore,this paper proposes a biomimetic adaptive memristive CNN (BAM-CNN) that combines CNNs, human visualadaptive tri-Gaussian theory and memristor, and nano information devices. The proposed CNN can be used forimage enhancement.
56573	其中,基于忆阻器的可编程性、非易失性、突触可塑性等优点,构建忆阻细胞神经网络架构.	Specifically, the memristive CNN is constructed based on emerging memristors that areprogrammable, non-volatile, and synapse-plastic.
56574	基于神经元感受野三高斯模型,利用高斯核函数和细胞神经网络的图像处理特征,提出对应的仿生自适应图像增强模板设计算法.	Merged with the tri-Gaussian model for the receptive field ofneurons, an adaptive CNN template design algorithm for biomimetic image enhancement is proposed using theimage processing features of the Gaussian kernel function and CNNs.
56575	最后,分别以灰度和彩色图像为例进行了图像增强实验和对比分析,结果表明,提出的仿生自适应忆阻细胞神经网络能够显著提高图像的全局亮度、局部对比度和清晰度.	In this paper, gray-scale and color imagesare taken as target examples in image enhancement experiments. The experimental results demonstrate that theproposed BAM-CNN significantly improves the global brightness, local contrast, and sharpness of the image. Thispaper provides a novel design and implementation scheme for adaptive templates of CNNs, which can improveCNNs’ biomimetic characteristics and hardware implementation feasibility.
56576	本研究可为细胞神经网络提供自适应模板设计及实现方案,提升细胞神经网络的仿生特性和硬件实现的可行性,并为图像增强等智能图像处理提供新思路.	The proposed BAM-CNN can be usedto develop innovative techniques for intelligent image processing besides image enhancement.
56577	在很多在线推荐系统场景中,用户和系统的交互通常都会按照时间间隔划分成一系列的会话.	In many online systems where recommendations are applied, interactions between a user and thesystem are usually organized into sessions.