|
所在平台: Udemy |
课程主页: https://www.udemy.com/course/machine-learning-course-with-python/
课程评论：没有评论
**课程名称：** Complete Machine Learning Course with Python **课程概述：** 本课程全面更新至 2019 年 11 月，旨在帮助学习者掌握机器学习的方方面面。课程涵盖了深度学习基础（如经典编程与机器学习、机器学习与深度学习的区别、神经网络构建模块、张量及其操作、机器学习分类、过拟合与欠拟合、正则化、Dropout、验证与测试等），以及计算机视觉（卷积神经网络，包括层构建、滤波器/核理解、迁移学习和特征提取）。 课程代码已更新至 Python 3.6 和 3.7，并优化以兼容 Google Colab。同时，课程内容也加入了深度学习与自然语言处理（NLP）、二分类与多分类深度学习等主题。 完成课程后，您将拥有一个包含 12 个机器学习项目的作品集，这有助于您获得理想工作或应用机器学习解决实际问题。课程讲师 Anthony NG 将带领您从零开始，一步步构建各种算法。您将学习如何： * 掌握解决现实问题的完整机器学习工具集。 * 理解各种回归、分类及其他机器学习算法的性能指标（如 R-squared, MSE, accuracy, confusion matrix, precision, recall 等）及其使用场景。 * 通过 Bagging、Boosting 或 Stacking 组合多个模型。 * 利用非监督学习算法（如层次聚类、K-Means 聚类）理解数据。 * 使用 Jupyter (IPython) notebook、Spyder 及各种 IDE 进行开发。 * 使用 Matplotlib 和 Seaborn 进行有效的视觉化交流。 * 工程化新特征以提升算法预测性能。 * 运用交叉验证（train/test, K-fold, Stratified K-fold）选择正确模型并预测其在未见过数据上的表现。 * 使用 SVM 进行手写识别和分类问题。 * 使用决策树预测员工离职倾向。 * 将关联规则应用于零售购物数据集。 **先修要求：** 无机器学习基础要求，但具备基础 Python 知识将有帮助。所有代码均会提供，并有详细讲解。 **适合人群：** 希望进入机器学习领域、获得数据科学家薪资的个人。 **课程亮点：** * 超过 18 小时内容。 * 已获得超过五十个五星好评，被认为是（Udemy 上）最长且评价最高的机器学习课程。 * 项目驱动式教学，动手实践。 * 目标是培养机器学习工程师。
The Complete Machine Learning Course in Python has been FULLY UPDATED for November 2019!With brand new sections as well as updated and improved content, you get everything you need to master Machine Learning in one course! The machine learning field is constantly evolving, and we want to make sure students have the most up-to-date information and practices available to them:Brand new sections include:Foundations of Deep Learning covering topics such as the difference between classical programming and machine learning, differentiate between machine and deep learning, the building blocks of neural networks, descriptions of tensor and tensor operations, categories of machine learning and advanced concepts such as over- and underfitting, regularization, dropout, validation and testing and much more.Computer Vision in the form of Convolutional Neural Networks covering building the layers, understanding filters / kernels, to advanced topics such as transfer learning, and feature extractions.And the following sections have all been improved and added to:All the codes have been updated to work with Python 3.6 and 3.7The codes have been refactored to work with Google ColabDeep Learning and NLPBinary and multi-class classifications with deep learningGet the most up to date machine learning information possible, and get it in a single course! * * *The average salary of a Machine Learning Engineer in the US is $166,000! By the end of this course, you will have a Portfolio of 12 Machine Learning projects that will help you land your dream job or enable you to solve real life problems in your business, job or personal life with Machine Learning algorithms.Come learn Machine Learning with Python this exciting course with Anthony NG, a Senior Lecturer in Singapore who has followed Rob Percival's "project based" teaching style to bring you this hands-on course.With over 18 hours of content and more than fifty 5 star ratings, it's already the longest and best rated Machine Learning course on Udemy!Build Powerful Machine Learning Models to Solve Any ProblemYou'll go from beginner to extremely high-level and your instructor will build each algorithm with you step by step on screen.By the end of the course, you will have trained machine learning algorithms to classify flowers, predict house price, identify handwritings or digits, identify staff that is most likely to leave prematurely, detect cancer cells and much more! Inside the course, you'll learn how to:Gain complete machine learning tool sets to tackle most real world problemsUnderstand the various regression, classification and other ml algorithms performance metrics such as R-squared, MSE, accuracy, confusion matrix, prevision, recall, etc. and when to use them.Combine multiple models with by bagging, boosting or stackingMake use to unsupervised Machine Learning (ML) algorithms such as Hierarchical clustering, k-means clustering etc. to understand your dataDevelop in Jupyter (IPython) notebook, Spyder and various IDECommunicate visually and effectively with Matplotlib and SeabornEngineer new features to improve algorithm predictionsMake use of train/test, K-fold and Stratified K-fold cross validation to select correct model and predict model perform with unseen dataUse SVM for handwriting recognition, and classification problems in generalUse decision trees to predict staff attritionApply the association rule to retail shopping datasetsAnd much much more!No Machine Learning required. Although having some basic Python experience would be helpful, no prior Python knowledge is necessary as all the codes will be provided and the instructor will be going through them line-by-line and you get friendly support in the Q & A area. Make This Investment in YourselfIf you want to ride the machine learning wave and enjoy the salaries that data scientists make, then this is the course for you!Take this course and become a machine learning engineer!
