|
所在平台: Udemy |
课程主页: https://www.udemy.com/course/machine-learning-project-guidelines/
课程评论：没有评论
课程名称：机器学习项目指南 概述：本课程由一位拥有超过20年IT行业经验、1.5年项目/程序管理经验及超过10年机器学习和数据科学独立研究经验的行业专家设计。课程旨在为学生提供扎实的理论基础和实践技能，使其能够有效应用机器学习算法和模型。课程内容基于作者撰写的白皮书和书籍《机器学习项目指南》。 在构建高性能的机器学习模型时，关键不在于你了解多少算法，而在于你如何充分利用已掌握的知识。课程将阐明以下几个重要观点：没有一种最优算法能适用于所有预测建模问题；选择算法的因素；即使是简单的算法，如果能够妥善处理模型错误和通过超参数调优进行模型优化，亦可能超越复杂算法。 课程通过生动的可视化和动画展示概念，确保理解无误。课程共分为13个部分： 1. 引言 2. 业务理解 3. 数据理解 4. 研究 5. 数据预处理 6. 模型开发 7. 模型训练 8. 模型优化 9. 模型评估 10. 最终模型选择 11. 模型验证与部署 12. 机器学习项目实操 13. 祝贺与结束语 该课程包括48节讲座、17个实操环节及29个可下载资产。完成课程后，学生将在求职面试中显著优于未参加该课程的候选人。
This course is designed by an industry expert who has over 2 decades of IT industry experience including 1.5 decades of project/ program management experience, and over a decade of experience in independent study and research in the fields of Machine Learning and Data Science.The course will equip students with a solid understanding of the theory and practical skills necessary to work with machine learning algorithms and models.This course is designed based on a whitepaper and the book "Machine Learning Project Guidelines" written by the author of this course.When building a high-performing ML model, it's not just about how many algorithms you know; instead, it's about how well you use what you already know.You will also learn that: There is NO single best algorithm that would work well for all predictive modeling problems And, the factors that determine which algorithm to choose for what type of problem(s) Even simple algorithms may outperform complex algorithms if you know how to handle model errors and refine the models through hyperparameter tuningThroughout the course, I have used appealing visualization and animations to explain the concepts so that you understand them without any ambiguity.This course contains 13 sections:IntroductionBusiness UnderstandingData UnderstandingResearchData PreprocessingModel DevelopmentModel TrainingModel RefinementModel EvaluationFinal Model SelectionModel Validation & Model DeploymentML Projects Hands-onML Project Template BuildingML Project 1 (Classification)ML Project 2 (Regression)ML Project 3 (Classification)ML Project 4 (Clustering - KMeans)ML Project 5 (Clustering - RFM Analysis)13. Congratulatory and Closing NoteThis course includes 48 lectures, 17 hands-on sessions, and 29 downloadable assets.By the end of this course, I am confident that you will outperform in your job interviews much better than those who have not taken this course, for sure.
