• Stochastic gradient descent method for machine learning


    batch In the gradient descent method, batch refers to the total number of samples used to calculate the gradient in a single iteration. So far, we have assumed that batch refers to the entire data set. In terms of Google’s scale, data sets usually include billions or even hundreds of billions of samples. In addition, […]

  • Logistic regression in machine learning: model training


    Loss function of logistic regression The loss function of linear regression is the square loss. The loss function of logistic regression is a logarithmic loss function, which is defined as follows: \displaystyle LogLoss = \sum_{(x,y)\in D} – ylog(y’) – (1-y)log(1-y’) Of which:1. (x, y) \ in D is a dataset containing many labeled samples (x, […]

  • Basic data structure and algorithm k-means clustering algorithm


    origin Recently read < < my first algorithm book > > ([Japan] Ishida Baohui; Miyazaki Xiuyi)This series of notes is intended to use golang exercises K-means clustering algorithm Clustering is when multiple data are input, The operation of grouping “similar” data into groups. K-means algorithm is one of clustering algorithms. Firstly, k points are randomly […]

  • K-means clustering algorithm


    K-means clustering algorithm clustering In unsupervised learning, the labeled information of training samples is unknown. The goal is to reveal the internal properties and laws of data through the learning of unmarked training samples, so as to provide a basis for further data analysis. Clustering is the most studied and widely used in this kind […]

  • Classification of machine learning: ROC and area under curve


    ROC curve ROC curve (receiver operating characteristic curve)It is a chart showing the effect of classification model under all classification thresholds. The curve draws the following two parameters: Real interest rate False positive interest rate Real interest rate (TPR)Is a synonym for recall rate, so it is defined as follows: TPR = \dfrac{TP}{TP + FN} […]

  • SQL ranking questions, 100% leetcode answers open!


    (first of all, forgive me for reading too much recently and giving me the name of secondary 2) I’m looking for an internship recently, so I plan to systematically summarize (review) the problems often encountered in SQL. Whether it is to brush leetcode or Niuke’s SQL questions, there is always a problem that can’t be […]

  • Super detailed DOM operation of jQuery, one article is enough!


    Summary:Today, I’d like to share with you the technologies related to DOM operation in the jQuery framework. It’s also an explanation of the DOM “family bucket” series. It’s recommended to collect, pay attention and study hard! This article is shared from Huawei cloud community《[jQuery framework] super detailed DOM operation. Just read this article!》Original author: grey […]

  • Classification of machine learning: true and false, positive and negative categories


    In this section, we will define the main components of the indicators used to evaluate the classification model. But let’s start with a fable:Aesop’s Fable: the wolf is coming (introduction version)A shepherd boy had to look after the sheep in the town, but he began to get tired of the job. In order to have […]

  • Clean up data for machine learning


    Apple trees produce both high-quality and moth eaten fruit. Apples sold in high-end convenience stores are 100% perfect fruit. From the orchard to the fruit store, someone spends a lot of time removing bad apples or coating salvageable apples with a thin layer of wax. As a machine learning engineer, You will spend a lot […]

  • Watermelon book Exercises – Chapter 08 – Integrated Learning


    Try and answer series: “watermelon book” – try and answer exercises of Zhou Zhihua’s machine learning Series catalog[chapter 01: introduction][chapter 02: model evaluation and selection][chapter 03: linear model][chapter 04: decision tree][chapter 05: neural networks][chapter 06: support vector machine] Chapter 07: Bayesian classifier Chapter 08: Integrated Learning Chapter 09: clustering Chapter 10: dimension reduction and metric […]

  • Unveil the top AI model of KPI anomaly detection


    Abstract: the 2020gde global developer competition KPI anomaly detection has come to an end. The “atomic bomb from introduction to Mastery” from Futian Lianhua street in Shenzhen is lucky to achieve the top 1 in the general list. Here, I share with you the solutions of Futian Lianhua street in Shenzhen in this competition. GDE […]

  • Python obtains sample data or performs tasks proportionally


    Obtain sample data or perform tasks in proportion   By: guest granting QQ: 1033553122 development environment win 10 python 3.6.5   demand Given the proportion of samples in each category and the total number of samples, it is necessary to obtain the samples of these categories in proportion. For example, I have four kinds of […]