|
所在平台: Udemy |
课程主页: https://www.udemy.com/course/machine-learning-course-f/
课程评论：没有评论
课程名称：完整的机器学习课程 概述：本课程将涵盖以下主题：1. 机器学习基础知识 2. 监督学习与非监督学习 3. 线性回归 4. 逻辑回归 5. KNN算法 6. 朴素贝叶斯分类器 7. 随机森林算法 8. 决策树算法 9. 主成分分析 (PCA) 10. K均值聚类 11. 层次聚类。课程中将进行基于线性回归、逻辑回归、朴素贝叶斯、KNN算法、随机森林、决策树、K均值和PCA的实用练习，同时会有机器学习课程的选择题测试。 首先，我们将深入了解线性回归，学习如何预测连续变量，包括简单线性回归和多重线性回归、普通最小二乘法、模型测试、R方和调整后的R方。接着，我们将详细探讨逻辑回归，这是一种非常流行的分类模型，学习最大似然估计、特征缩放、混淆矩阵、准确率等，并成功构建第一个逻辑回归模型。 此外，我们会研究朴素贝叶斯分类器，内容包括贝叶斯定理以及朴素贝叶斯在机器学习中的实现，适用于垃圾邮件过滤、文本分析和推荐系统。随机森林算法适用于回归和分类问题，能在数据不完整的情况下保持良好准确性。决策树是一种监督学习技术，适用于分类和回归问题，但主要用于解决分类问题。 课程还将讲解KNN算法，包括KNN算法的工作原理、距离矩阵计算、Makowski距离，以及KNN在行业中的实际应用示例。同时，我们将探讨主成分分析（PCA）、K均值聚类和层次聚类，这些属于非监督学习部分。 在监督学习和非监督学习的各个环节中，我们将跟随数据读取、数据预处理、探索性数据分析（EDA）、数据缩放，以及训练和测试数据的准备，最终进行机器学习模型的选择、实现和预测。
This course will cover following topics1. Basics of machine learning2. Supervised and unsupervised learning3. Linear regression 4. Logistic regression5. KNN Algorithm6. Naive Bayes Classifier7. Random forest Algorithm8. Decision Tree Algorithm7. Principal component analysis8. K means clustering9. Agglomerative clustering10. There will practical exercise based on Linear regression, Logistic regression ,Naive Bayes, KNN algorithm, Random forest, Decision tree, K Means, PCA.11. Quiz (MCQ on machine learning course)We will look first in to linear Regression, where we will learn to predict continuous variables and this will details of Simple and Multiple Linear Regression, Ordinary Least Squares, Testing your Model, R Squared and Adjusted R Squared.We will get full details of Logistic Regression, which is by far the most popular model for Classification. We will learn all about Maximum Likelihood, Feature Scaling, The Confusion Matrix, Accuracy Ratios and you will build your very first Logistic RegressionWe will look in to Naive bias classifier which will give full details of Bayes Theorem, implementation of Naive bias in machine learning. This can be used in Spam Filtering, Text analysis, Recommendation Systems.Random forest algorithm can be used in regression and classification problems. This gives good accuracy even ifdata is incomplete.Decision Tree is a Supervised learning technique that can be used for both classification and Regression problems, but mostly it is preferred for solving Classification problems.We will look in to KNN algorithm which will working way of KNN algorithm, compute KNN distance matrix, Makowski distance, live examples of implementation of KNN in industry.We will look in to PCA, K means clustering, Agglomerative clustering which will be part of unsupervised learning.Along all part of machine supervised and unsupervised learning , we will be following data reading , data prerprocessing, EDA, data scaling, preparation of training and testing data along machine learning model selection , implemention and prediction of models.
