• ## Generate the understanding of confrontation network Gan and dcgan (pytorch+ teacher Li Hongyi homework 6)

Time：2022-7-31

The problems encountered by the author in Gan learning are summarized below and explained. The topic mentioned below is homework 6 (GAN) of Teacher Li Hongyi’s machine learning course 1、 Gan There are many explanations about Gan and dcgan on the Internet, so I won’t repeat them here. Let’s put some explanations that I think […]

• ## Extended tecdat|r language ggplot2 error bar chart Quick Guide

Time：2022-7-17

Original link:http://tecdat.cn/?p=5506 Add error bars to histograms and line graphs Prepare data The toothgrowth dataset is used here. library(ggplot2)  df <- ToothGrowth  df\$dose <- as.factor(df\$dose)  head(df)  ## len supp dose ## 1 4.2 VC 0.5 ## 2 11.5 VC 0.5 ## 3 7.3 VC 0.5 ## 4 5.8 VC 0.5 ## 5 6.4 VC 0.5 ## 6 10.0 VC 0.5 Len: tooth length Dose: the unit of dose (0.5, 1, 2) is mg Sup: support type (VC or OJ) In the following example, we will plot the average length of teeth in […]

• ## NF RESNET: remove BN normalization, network signal analysis worthy of careful reading | ICLR 2021

Time：2022-7-6

This paper proposes NF RESNET, which analyzes the actual signal transmission of the network, simulates the performance of batchnorm in the transmission of mean and variance, and then replaces batchnorm. The experiment and analysis of the paper are very sufficient, and the effect is also very good. The theoretical effect of some initialization methods is […]

• ## Mean regression

Time：2022-6-24

After reading simple statistics, I learned some scientific but incorrect phenomena or conclusions. I am more interested in survivor bias and mean regression. No matter the best sellers we have read, or others, we always like to summarize some seemingly rules or characteristics, such as the characteristics of a great company, the reasons why so […]

Time：2022-5-24

Original link:http://tecdat.cn/?p=24814 When it comes to making money in the stock market, there are countless different ways to make money. It seems that in the financial world, wherever you go, people are telling you that you should learn python. After all, Python is a popular programming language that can be used in all types of […]

• ## R language arima-garch volatility model predicts the daily return time series of apple in the stock market

Time：2022-5-4

Original link:http://tecdat.cn/?p=23934 introduction In this paper, we will try to find a suitable GARCH model for Apple’s daily return. Volatility modeling requires two main steps. Specify a mean equation (e.g. ARMA, AR, Ma, ARIMA, etc.). Establish a volatility equation (such as GARCH and arch, which were first developed by Robert Engle). To do (1), you […]

• ## Quantitative Ecology: application of R language Chapter 4 cluster analysis 3 – non hierarchical clustering

Time：2022-4-11

Quantitative Ecology: application of R language Chapter 4 cluster analysis 3 – non hierarchical clustering Hierarchical clustering is often used in cluster analysis. Hierarchical clustering calculates the similarity between nodes through a certain similarity measure, sorts them from high to low, and gradually reconnects nodes. Another kind of non hierarchical clustering is a simple grouping […]

• ## Regional system transfer trading strategy based on GARCH Volatility Prediction in R language

Time：2022-4-4

Original link:http://tecdat.cn/?p=17526 Original source:Tuo end data tribal official account This paper proposes an algorithm, which can switch between mean regression and trend following strategy according to market volatility. Two models are studied: one uses historical volatility and the other uses GARCH (1,1) volatility prediction. The mean regression strategy uses RSI (2) for modeling: it is […]

• ## Data processing cornerstone: Pandas data exploration

Time：2022-3-31

Preliminary exploration of pandas data This paper introduces the preliminary exploration of pandas data. After we generate or import data, we can quickly understand and understand the basic information of the data through data exploration, such as the type, index, maximum value and missing value of the fields in the data, which can give us […]

• ## Function and usage of dplyr package

Time：2022-3-22

See which functions are in the dplyr package library(dplyr) ls(‘package:dplyr’) #There are currently 290 packages 1: Filter function 1.1 filter function ⚠️ in the light ofthat ‘s okOperate to extract an observation in one or more grouped variables library(dplyr) The demo data set used by Library (reshape2) # comes from this package #Select the non-smoking […]

• ## Machine learning algorithm series (x) – linear discriminant analysis algorithm (I)

Time：2022-2-25

Background knowledge required for reading this article: Lagrange multiplier method and yidui programming knowledge 1、 Introduction    I learned a classification algorithm using regression – logarithmic probability regression algorithm. Now I’ll learn another classification algorithm——Linear discriminant analysis algorithm1(linear discriminant analysis algorithm / LDA), which was proposed by Ronald Elmer Fisher in 1936, is also known […]

• ## Adding p value for ggprism packet data visualization

Time：2022-2-21

It can be said that one of the most popular functions of graphpad prism is to add p value to the drawing,Ggprism usageadd_pvalue()Add a p value with or without brackets; Love little buddy can pay attention to my official account.R language data analysis guideContinuously analyze more high-quality resources library(tidyverse) library(ggprism) library(patchwork) library(magrittr) p <- ggplot(sleep, […]