|
所在平台: Udemy |
课程主页: https://www.udemy.com/course/machine-learning-and-deep-learning-in-one-semester/
课程评论：没有评论
课程名称：机器学习与深度学习大师班（一个学期） 课程概述： 本课程全面介绍机器学习和深度学习的基本理论与实践，适合希望深入了解这一领域的学习者。课程内容涵盖从Python基础知识到各种机器学习与深度学习模型的构建和应用，帮助学员掌握关键技能。 学习内容包括： - 机器学习与深度学习简介 - 数据预处理及Python快速入门 - 有监督学习中的回归分析与分类模型，如逻辑回归、K最近邻（KNN）、朴素贝叶斯分类器、支持向量机（SVM）、决策树、随机森林及提升方法 - 深度学习基础，包括神经网络的工作原理、激活函数、损失函数、反向传播 - 使用神经网络进行回归与分类分析 - 深度学习中的正则化方法（如Dropout和Batch Normalization） - 卷积神经网络（CNN）与循环神经网络（RNN）的应用 - 自编码器与生成对抗网络（GAN）的概念与实现 - 无监督学习方法，如K均值聚类、层次聚类、基于密度的聚类（DBSCAN）、高斯混合模型（GMM）聚类及主成分分析（PCA） - 实际项目实践，完成超过80个应用机器学习与深度学习模型的项目 通过本课程，学员将掌握机器学习和深度学习算法的理论、数学基础及其实现，能够构建人工神经网络并解决实际问题，并熟练运用Python及相关库（如NumPy、Matplotlib、Pandas、PyTorch、scikit-learn等）。
IntroductionIntroduction of the CourseIntroduction to Machine Learning and Deep LearningIntroduction to Google ColabPython Crash CourseData PreprocessingSupervised Machine LearningRegression AnalysisLogistic RegressionK-Nearest Neighbor (KNN)Bayes Theorem and Naive Bayes ClassifierSupport Vector Machine (SVM)Decision TreesRandom ForestBoosting Methods in Machine LearningIntroduction to Neural Networks and Deep LearningActivation FunctionsLoss FunctionsBack PropagationNeural Networks for Regression AnalysisNeural Networks for ClassificationDropout Regularization and Batch NormalizationConvolutional Neural Network (CNN)Recurrent Neural Network (RNN)AutoencodersGenerative Adversarial Network (GAN)Unsupervised Machine LearningK-Means ClusteringHierarchical ClusteringDensity Based Spatial Clustering Of Applications With Noise (DBSCAN)Gaussian Mixture Model (GMM) ClusteringPrincipal Component Analysis (PCA)What you'll learnTheory, Maths and Implementation of machine learning and deep learning algorithms.Regression Analysis.Classification Models used in classical Machine Learning such as Logistic Regression, KNN, Support Vector Machines, Decision Trees, Random Forest, and Boosting Methods in Machine Learning.Build Artificial Neural Networks and use them for Regression and Classification Problems.Using GPU with Deep Learning Models.Convolutional Neural NetworksTransfer LearningRecurrent Neural NetworksTime series forecasting and classification.AutoencodersGenerative Adversarial NetworksPython from scratchNumpy, Matplotlib, seaborn, Pandas, Pytorch, scikit-learn and other python libraries.More than 80 projects solved with Machine Learning and Deep Learning models.
