Oxford__Parallel-Scientific-Computation

源负载耦合耦合矩阵程序 源负载耦合耦合矩阵程序源负载耦合耦合矩阵程序(source and load coupling matrix )

深度学习的中文版本，里面详细介绍了深度学习的各种算法，其中还有一些用到的基础内容，例如矩阵和向量的范数(Chinese version of the depth of learning, which detailed the depth of learning algorithms, some of which used the basics, such as vector and matrix norm)

多线程pthread实现对一个给定矩阵求取卷积，并将结果保存下来(Pthread multithreading to achieve a given matrix convolution to strike, and the result is saved)

LU算法的MPI串行实现，矩阵维数无要求，可在曙光4000A并行机运行(The LU algorithm MPI serial implementation matrix dimension requirements Dawning 4000A parallel machine running)

利用Python实现特征的MinMax标准化和Z-Score标准化两种特征归一化方法。并用原特征、两种归一化特征分别进行模型训练，比较模型性能。(Two normalization methods of MinMax normalization and Z-Score standardization are implemented by Python. The model is trained by the original feature and two normalization features respectively, and the performance of the model is compared.)

OpenCL1.2版本的扩展功能用户手册。(OpenCL1.2 version of the Expansion Function User' s Manual.)

研究多目标遗传算法的优化，包含遗传算法过程中涉及的的各个步骤，非常适合于研究遗传算法及对遗传算法进行多目标优化的同学

实现单GPU二维弹性波全波形反演，采用c++和CUDA c编写，VS2013开发。(2D elastic Full waveform Inversion using a single GPU card, based on C++/CUDA c language, developed by VS2013.)

说明：  深度学习的中文版本，里面详细介绍了深度学习的各种算法，其中还有一些用到的基础内容，例如矩阵和向量的范数(Chinese version of the depth of learning, which detailed the depth of learning algorithms, some of which used the basics, such as vector and matrix norm)

说明：  本文介绍的基于多线程和图像分块实现加速运算，因为调用了opencv库，比较容易编写和实现。OpenCV全称是是Open Source Computer Vision Library，它是由Intel微处理器研究实验室的视觉交互组开发，是一种用于数字图像处理和计算机视觉的开源函数库，采用的开发语言是C++。(This paper introduces an acceleration algorithm based on multi-threading and image partitioning, because it is easy to write and implement by calling the opencv library. OpenCV is called Open Source Computer Vision Library. It is developed by the Visual Interaction Group of Intel Microprocessor Research Laboratory. It is an open source library for digital image processing and computer vision. The development language used is C++)