• Machine learning (13): Wu Enda’s notes


    Previously, we have learned a series of supervised learning algorithms such as linear regression, logical regression and neural network, and come to the conclusion: in machine learning, the important thing is not to use algorithm a or algorithm B, but to collect a large amount of data. And the performance of the algorithm depends on […]

  • Machine learning (16): Wu Enda’s notes


    The most popular dimension reduction algorithm: principal component analysis (PCA) Before applying PCA, we should normalize the mean value and normalize the features, so that the values can be compared PCA target When we reduce the data set from two dimensions to one dimension, we need to find a vector to make the distance between […]

  • Intuitive interpretation of neural machine translation


    By ReNu Khandelwal What is neural machine translation? Neural machine translation is a technology that translates one language into another. One example is the conversion of English to Hindi. Let’s think about it. If you’re in an Indian village, most of the people there don’t know English. You plan to communicate with the villagers effortlessly. […]

  • Linear discriminant analysis, LDA


    Linear discriminant classifier consists of vector $W $and deviation term $B $. Given the example $x $, it predicts the category tag $y $according to the following rules, that is$y=sign(w^Tx+b)$The column vector is represented by lowercase and row vector is represented by transposition.The classification process is divided into two steps Firstly, the weight vector w […]

  • Tikv source code analysis series (15) expression calculation framework


    Author: Luo Dean The last article “tikv source code analysis series (XIV) coprocessor Overview” mentioned that in order to maximize the use of distributed computing power, tidb will try to push down the selection operator and aggregation operator to the tikv node. This article will continue to introduce the source code architecture of expression calculation […]

  • Engineering practice of map search system


    Engineering practice of map search system I wrote an overview before: an overview of image search system. The main problems to be solved in the system are as follows Extracting image feature vector (using eigenvector to represent an image) Similarity calculation of feature vectors (searching for images with similar contents) The corresponding engineering practices are […]

  • GIS vector slicing algorithm (Reprint)


    Transferred from: https://www.giserdqy.com/database/postgresql/25838/ For large-scale vector data, due to the large number of types and wide range of data, loading and rendering will cause the platform to be stuck. Therefore, the quadtree index slicing of vector data can efficiently load the current region vector and improve the efficiency. The common vector data is ShapeFile, which […]

  • Linear algebra knowledge in reinforcement learning


    By Nathan LambertCompile | VKSource: toward Data Science How can the basic principles of linear algebra be used in deep reinforcement learning? The answer is to solve the iterative update in Markov decision process. Reinforcement learning (RL) is a series of intelligent methods for iterative learning tasks. Because computer science is a computing field, this […]

  • How do neural networks learn?


    Introduction:There is no doubt that neural network is the most popular machine learning technology. So I think it’s very meaningful to understand how neural networks learn. Like going downhill, find the lowest point of the loss function. There is no doubt that neural network is the most popular machine learning technology. So I think it’s […]

  • Wu Enda EX4


    ex4 The main difficulty of this topic is to realize the back propagation algorithm. The algorithm steps are as follows: 1. For each sample (x (I), y (I)) Order a_ 1 = x (I), Z is calculated respectively_ 2 、a_ 2、Z_ 3、a_ 3;      Z_i = Theta(i-1)*a(i-1); A_ I = Supplement 1 + sigmoid […]

  • Algorithm Engineering II. Mathematical basis linear algebra


    Linear algebra content is very coherent, the whole is [determinant > matrix > n-dimensional vector > linear equations system > similar diagonal type > quadratic form]. The determinant is a value. If the determinant is 0, the corresponding linear equations have multiple solutions, and the corresponding matrix is irreversible. If the determinant is 0, the […]

  • Collision detection: Triangle


    Introduction stayCollision Detection :PolygonThis paper mainly introduces the polygon related collision detection, and then look at the situation of triangles. Triangles also belong to polygons, so polygon method is applicable to triangles. Here’s another way of thinking. The following examples are not checked for compatibility and are recommended to be viewed in the latest chrome […]