|
所在平台: Udemy |
课程主页: https://www.udemy.com/course/dp-100-microsoft-azure-data-scientist-ds-exam-preparation/
课程评论：没有评论
课程名称：DP-100 Microsoft Azure 数据科学家（DS）考试准备 课程概述： 本课程旨在帮助学员为DP-100 Microsoft Azure 数据科学家认证考试做好准备。课程涵盖使用Azure机器学习设计和实施机器学习解决方案所需的所有关键主题。通过实践项目和深入的课程讲解，学员将获得实践经验和信心，以应对实际挑战并顺利通过认证考试。 第一部分：介绍 介绍课程内容，概述目标，并解读考试要求。让学员了解他们将要达成的目标以及所需掌握的技能。 第二部分：创建Azure机器学习工作区 学习如何创建Azure ML工作区，管理设置，并导航Azure门户及ML Studio。这些基础知识能够确保学员为Azure的机器学习环境做好准备。 第三部分：Azure学习工作区 探索Azure ML中的数据存储和数据集管理。学习如何创建和管理数据集，为实验和机器学习管道准备数据。 第四部分：管理实验计算上下文 了解运行实验所需的计算实例和集群。该部分解释了如何设置和管理计算目标，以优化资源利用率和执行速度。 第五部分：使用Azure机器学习 创建首个机器学习管道并提交执行。深入了解自定义编码、错误处理，并探索Azure ML设计师的模块，构建稳健的管道。 第六部分：Azure机器学习体验 开始使用Azure SDK，以编程方式设置工作区，并创建简单的Python程序。学习Azure的SDK如何简化机器学习任务。 第七部分：在Azure机器学习环境中运行训练 使用SDK训练模型，提交实验，并创建复杂的管道。该部分重点介绍实践培训和高效工作流程的自动化技术。 第八部分：自动化机器学习以创建最佳模型 掌握Azure AutoML，自动化模型选择、调优和部署。学习如何使用SDK与AutoML达到最佳效果，减轻工作负担。 第九部分：使用Hyperdrive调优超参数 探索Hyperdrive，Azure的超参数调优工具。学习注册训练的模型，管理生产计算目标，并高效优化模型性能。 第十部分：将模型部署为服务 将模型部署用于实时推理或批处理。熟悉创建端点、部署基于SDK的模型，并发布大规模任务的管道。 第十一部分：结论 总结课程的关键学习内容，并讨论学员在Azure ML旅程中的潜在下一步，包括认证或高级实际项目。 本课程为您提供有效使用Azure ML构建、训练和部署机器学习模型的技能。无论您是初学者还是经验丰富的数据专业人士，实践项目和深入课程将确保您能够应对Azure强大工具包带来的机器学习挑战。
Course OverviewThis course is designed to prepare you for the DP-100 Microsoft Azure Data Scientist Certification Exam. It covers all the critical topics required to design and implement machine learning solutions using Azure Machine Learning. Through hands-on projects and in-depth lessons, you'll gain practical experience and the confidence to tackle real-world challenges and ace the certification exam.Section 1: IntroductionThis section introduces the course, outlines its objectives, and explains the exam requirements. It sets the stage by familiarizing students with what they'll achieve and the skills they'll gain.Section 2: Create an Azure Machine Learning WorkspaceLearn how to create an Azure ML workspace, manage its settings, and navigate the Azure portal and ML Studio. This foundational knowledge ensures you're ready to work in Azure's machine-learning environment.Section 3: Azure Learning WorkspaceExplore data storage and dataset management within Azure ML. Learn how to create and manage datasets, preparing data for experiments and machine-learning pipelines.Section 4: Manage Experiment Compute ContextUnderstand compute instances and clusters for running experiments. This section explains setting up and managing compute targets to optimize resource utilization and execution speed.Section 5: Using Azure Machine LearningCreate your first machine-learning pipeline and submit it for execution. Dive into custom coding, error handling, and exploring Azure ML Designer's modules to build robust pipelines.Section 6: Azure Machine Learning ExperienceGet started with Azure SDK, set up your workspace programmatically, and create simple Python programs. Learn how Azure's SDK streamlines ML tasks.Section 7: Run Training in an Azure Machine Learning EnvironmentUse the SDK to train models, submit experiments, and create complex pipelines. This section focuses on hands-on training and automation techniques for efficient workflows.Section 8: Automate ML to Create Optimal ModelsMaster Azure AutoML to automate model selection, tuning, and deployment. Learn how to use AutoML with SDK to achieve optimal results with minimal effort.Section 9: Use Hyperdrive to Tune HyperparametersExplore Hyperdrive, Azure's hyperparameter tuning tool. Learn to register trained models, manage production compute targets, and optimize model performance efficiently.Section 10: Deploy Model as a ServiceDeploy models for real-time inference or batch processing. Gain expertise in creating endpoints, deploying SDK-based models, and publishing pipelines for large-scale tasks.Section 11: ConclusionWrap up the course with a summary of the key learnings and discuss the potential next steps in your Azure ML journey, including certification or advanced real-world projects.This course equips you with the skills to use Azure ML effectively for building, training, and deploying machine-learning models. Whether you're a beginner or an experienced data professional, the hands-on projects and in-depth lessons will ensure you're ready to tackle ML challenges with Azure's robust toolkit.
