[machine learning] use pyplot to draw handwritten digits in MNIST dataset

MNIST data set is a set of handwritten digital data set given by Yann LeCun, the leader of artificial intelligence. The training set contains 60000 samples and labels, and the test set contains 10000 samples and labels. It can be used for novices to practice their hands. Dataset representation Annotation: the number is divided into 0-9, a t ...

Posted by WLW on Mon, 24 Jan 2022 07:13:15 +0100

Training skill improvement of GAN (WGAN, LSGAN, EBGAN, WGAN-GP algorithm) with code

Description of several problems in generating countermeasure networks What is information entropy? We use entropy to measure whether the data is ordered or disordered Calculating information entropy Information entropy is a measure of system chaos: Where Pi represents the probability of an event, the minimum information entropy is 0, ...

Posted by gszauer on Mon, 24 Jan 2022 05:31:54 +0100

Common evaluation indicators for deep learning classification tasks

Abstract: This article mainly introduces the evaluation indicators of deep learning classification tasks, including basic application, practical skills, principles and mechanisms, hoping to be helpful to you. This article is shared from Huawei cloud community< Common evaluation indicators for deep learning classification tasks >Original ...

Posted by TKKP on Mon, 24 Jan 2022 02:43:15 +0100

Jupyter / Part 1 Chapter 2 / converter

converter Most machine learning algorithms are easier to deal with numbers, so let's turn these texts into numbers first. sklearn provides a converter for such tasks. Data to convert # Load Library import os import tarfile import pandas as pd from six.moves import urllib DOWNLOAD_ROOT = "https://raw.githubusercontent.com/ageron/handson-ml/m ...

Posted by Melville on Mon, 24 Jan 2022 01:00:11 +0100

Three common methods of t-test and examples used in Python

T-test is a statistical technique that can tell people how significant the difference between two groups of data is. It is achieved by comparing the semaphore (measured by the difference between samples or population averages) with the amount of noise (or change) in these samples. There are many useful articles that will tell you what t-tests a ...

Posted by Tremor on Sun, 23 Jan 2022 19:14:50 +0100

Recognizer based on opencv

1 problem background Biometric technology is widely used in government, military, banking, social welfare, e-commerce, security and defense and other fields. With the further maturity of technology and the improvement of social recognition, face recognition technology included in biometric technology will be applied in more fields, such as: 1. ...

Posted by srfdriver22 on Sun, 23 Jan 2022 11:41:31 +0100

MNIST handwritten numeral recognition with PyTorch (latest, very detailed)

introduction Based on PyTorch framework, this paper uses CNN convolutional neural network to realize MNIST handwritten numeral recognition, which runs only on CPU. Four structures, Linear pure Linear layer, CNN convolutional neural network, Inception network and Residual residual network, have been used to recognize handwritten digits fro ...

Posted by Vidya_tr on Sun, 23 Jan 2022 08:49:39 +0100

Feature Engineering - Data Preprocessing

1 exploratory data analysis Data were used: Pima Indian diabetes prediction dataset. Link: https://pan.baidu.com/s/17M7UfnqGYTkpLmCXUOyTkw Extraction code: y4fz import pandas as pd pima_column_names = ['times_pregnant', 'plasma_glucose_concentration', 'diastolic_blood_pressure', 'triceps_thickness', ' ...

Posted by Dilbert137 on Sat, 22 Jan 2022 21:23:37 +0100

Detailed explanation of the events of the Kaggle Titanic

Data link: https://pan.baidu.com/s/1gE4JvsgK5XV-G9dGpylcew Extraction code: y409 Project background 1. Titanic: an Olympic class cruise ship under the jurisdiction of British white star shipping company. It was built at Harland and Wolff shipyard in Belfast port, Ireland on March 31, 1909. It was launched on May 31, 1911 and complete ...

Posted by dgwade on Sat, 22 Jan 2022 21:01:07 +0100

R language principal component analysis PCA spectral decomposition, singular value decomposition SVD prediction analysis of athlete performance data and dimensionality reduction visualization

Original link: http://tecdat.cn/?p=25067 This paper describes how to} perform principal component analysis (PCA) using R. You will learn how to} use PCA_ Forecast_ New individual and variable coordinates. We will also provide_ PCA results_ The theory behind it.There are two general methods to perform PCA in R:_ Spectral decomposition_ , check t ...

Posted by merebel on Sat, 22 Jan 2022 16:20:18 +0100