在计算机实验（DoCE）设计领域，拉丁超立方体设计经常用于黑盒的近似和优化。 在某些情况下，我们需要一种特殊类型的设计，其中包括两个独立的设计，一个是另一个的子集。 这些嵌套的设计可用于处理训练和测试集，具有不同精度级别的模型，链接参数以及顺序评估。 在本文中，我们最多可构建10个嵌套的maximin拉丁超立方体设计。 我们展示了在构建嵌套设计时应考虑不同类型的网格，并讨论如何确定用于特定应用程序的网格。 为了确定尺寸大于2的嵌套maximin设计，Jin等人的ESE算法有四个不同的变体。 （2005）进行了介绍和比较。 在附录中，提供了不同数量点的最大距离。

这个软件库包含的代码运行中存在的实验。 此处的代码被冻结为最初编写本文时的代码。 如果您对使用LIME感兴趣，请查看，我们将其打包在其中，提高了代码质量，增加了可视化效果和其他改进。 运行以下命令应该足以获取所有结果。 您需要特定版本的python，sklearn，numpy，scipy。 使用以下命令在virtualenv中安装要求： pip install -r requirements.txt 如果我们忘记了什么，请给第一作者发电子邮件。 在5.2节中进行实验： 数据集->'multi_polarity_books'，'multi_polarity_kitchen'，'multi_polarity_dvd'，'multi_polarity_kitchen' 算法->'l1logreg'，'tree' 解释器->“石灰”，“ parzen”，“贪婪”或“随机” pyth

Design of Experiments for Engineers and Scientists Second Edition Design of Experiments (DOE) is a powerful technique used for both exploring new processes and gaining increased knowledge of existing processes, followed by optimising these processes for achieving world-class performance. My involvement in promoting and training in the use of DOE dates back to the mid-1990s. There are plenty of books available in the market today on this subject written by classic statisticians, although the majority of them are better suited to other statisticians than to run-of-the-mill industrial engineers and business managers with limited mathematical and statistical skills. DOE never has been a favourite technique for many of today’s engineers and managers in organisations due to the number crunching involved and the statistical jargon incorporated into the teaching mode by many statisticians. This book is targeted to people who have either been intimidated by their attempts to learn about DOE or who have never appreciated the true potential of DOE for achieving breakthrough improvements in product quality and process efficiency. This book gives a solid introduction to the technique through a myriad of practical examples and case studies. The second edition of the book has incorporated two new chapters and both cover the latest developments on the topic of DOE. Readers of this book will develop a sound understanding of the theory of DOE and practical aspects of how to design, analyse and interpret the results of a designed experiment. Throughout this book, the emphasis is on the simple but powerful graphical tools available for data analysis and interpretation. All of the graphs and figures in this book were created using Minitab version 15.0 for Windows. I sincerely hope that practising industrial engineers and managers as well as researchers in academic world will find this book useful in learning how to apply DOE in their own work environment. The book will also be a useful resource for people involved in Six Sigma training and projects related to design optimisation and process performance improvements. In fact, I have personally observed that the number of applications of DOE in non-manufacturing sectors has increased significantly because of the methodology taught to Six Sigma professionals such as Six Sigma Green Belts and Black Belts. The second edition has a chapter dedicated to DOE for non-manufacturing processes. As a mechanical engineer, I was not convinced about the application of DOE in the context of the service industry and public sector organisations including Higher Education. I have included a simple case study showing the power of DOE in a university setting. I firmly believe that DOE can be applied to any industrial setting, although there will be more challenges and barriers in the non-manufacturing sector compared to traditional manufacturing companies. I hope that this book inspires readers to get into the habit of applying DOE for problem-solving and process troubleshooting. I strongly recommend that readers of this book continue on a more advanced reference to learn about topics which are not covered here. I am indebted to many contributors and gurus for the development of various experimental design techniques, especially Sir Ronald Fisher, Plackett and Burman, Professor George Box, Professor Douglas Montgomery, Dr Genichi Taguchi and Dr Dorian Shainin.

Design And Analysis Of Experiments, 5Th Edition (Douglas C Montgomery)-Keep 试验设计与分析 5ed

在疯狂的实验中唇读 该存储库包含我在Keras中使用深度学习进行唇读的实验。 我训练并测试。 进程-lrw / 将LRW数据集中的视频转换为以下代码的代码：-与单词有关的帧-这些帧的嘴巴区域-音频 目录中的README文件中提供了说明。 形状预测器/ 放置process-lrw和head-pose所需的“ shape_predictor_68_face_landmarks.dat”文件的目录 图像检索/ 代码和文件---将lipreader视为图像检索系统 头姿势/ 代码和文件---计算LRW数据集中所有帧的头部姿势（使用process-lrw提取） 头部姿势是使用 （我的叉子）确定的。 目录中的README文件中提供了说明。

Digital Signal Processing- Laboratory Experiments Using C

使用KNearestNeighbor进行实验 前言 在模式识别和机器学习中，k最近邻算法（或简称k-NN）是用于分类和回归的非参数方法。 在这两种情况下，输入都包含的特征空间中的k个最接近的训练示例 实验 我开始这项工作，以比较在有无数据归一化的情况下，由KNN算法进行分类的准确性。 对于算法的准确性，我们是指正确分类的实例的百分比。 使用库sklearn用Python编写了代码，并且从流行的存储库UCI中下载了四个使用的数据集。 虹膜数据集[链接]（ ） 脑电图眼图状态 种子数据集 魔术伽玛望远镜 为了在终端上运行代码类型python knn_main.py ：计算K等于1,3,5,10的KNN。 结果 虹膜数据集：150个样本 1NN的精度：0.9533-带有归一化步骤的1NN的精度：0.9467 3NN的精度：0.9600-3NN归一化步骤的精度：0.9400 5NN的精度

星空直播 第一季第14課：具有抗干擾能力的Transformer對話系統Experiments詳解.mp4

CUDA实验 CUDA实验

HUST-OS-实验 必须在2018年Spring进行操作系统实验。 更新：在此仓库中添加夏季任务。 环境 gcc version 5.4.0 20160609 (Ubuntu 5.4.0-6ubuntu1~16.04.9 in Windows Subsystem Linux) Thread model: posix 文件 实验室目录 每个独立于其他实验室的代码，这些代码的可执行文件和一些测试文件 .vscode 在vscode-windows上运行linux c代码的配置 细节 实验1： 使用管道在两个过程之间传输数据。 实验2： 使用信号量来同步线程的行为。 实验3： 使用共享内存和信号量让两个进程按顺序复制数据。 labextra： 模拟linux基本功能'ls'。 实现的扩展参数： 指定路径 -l -lR lab_tinyOS TinyOS实验室包含几个部