|
所在平台: Coursera |
课程主页: https://www.coursera.org/learn/art-science-ml
课程评论：没有评论
课程名称：企业中的机器学习 课程概述：本课程采取真实世界的实用视角，介绍了机器学习（ML）工作流程。通过案例研究，参与者将了解ML团队如何面对多项ML业务需求和使用案例，并掌握数据管理和治理所需的工具。同时，课程将帮助学员选择最佳的数据预处理方法，包括Dataflow和Dataprep的概述以及使用BigQuery进行预处理任务。 课程中，团队将面对三种选择，以应对两个特定用例的机器学习模型构建需求。课程将解释为何选择AutoML、BigQuery ML或自定义训练来实现目标，并深入探讨自定义训练的要求，包括训练代码结构、存储、大数据集加载以及导出训练模型的过程。 学员将构建一个自定义训练的机器学习模型，能以较少的Docker知识构建容器镜像。此外，案例组还将研究如何使用Vertex Vizier进行超参数调优，以提高模型性能。为深入了解模型改进，课程探讨了正则化、稀疏处理及其他基本概念与原理。最后，课程将综述预测和模型监控，并讲解如何利用Vertex AI管理机器学习模型。 课程大纲： 1. 导言：提供课程及其目标的概述。 2. 理解机器学习企业工作流程：讨论ML企业工作流程及每个步骤的目的。 3. 企业中的数据：回顾Google的企业数据管理和治理工具：特征存储、数据目录、Dataplex和分析中心。 4. 机器学习科学与自定义训练：探讨机器学习和神经网络的艺术与科学，并讲解如何使用Vertex AI训练自定义ML模型。 5. Vertex Vizier超参数调优：讨论如何使用Vertex AI Vizier进行超参数调优。 6. 使用Vertex AI进行预测与模型监控：介绍通过预构建和自定义容器进行批量和在线预测，然后回顾模型监控，帮助管理ML模型的性能。 7. Vertex AI管道：讨论如何构建Vertex AI管道以协调机器学习工作流程。 8. 机器学习开发最佳实践：回顾在Vertex AI中不同机器学习过程的最佳实践。 9. 课程总结：对企业中的机器学习课程进行总结。 10. 系列总结：对Google Cloud上的机器学习课程系列进行总结。
Name:Introduction
Description:This module provides an overview of the course and its objectives.
Name:Understanding the ML Enterprise Workflow
Description:This module discusses the ML enterprise workflow and the purpose of each step.
Name:Data in the Enterprise
Description:This module reviews Google’s enterprise data management and governance tools: Feature Store, Data Catalog, Dataplex, and Analytics Hub.
Name:Science of Machine Learning and Custom Training
Description:This module reviews the art and science of machine learning and neural networks. We'll also discuss how to train custom ML models using Vertex AI.
Name:Vertex Vizier Hyperparameter Tuning
Description:In this module we discuss how to do hyperparameter tuning using Vertex AI Vizier.
Name:Prediction and Model Monitoring Using Vertex AI
Description:This module covers Vertex AI prediction and model monitoring. We'll first discuss batch and online predictions using pre-built and custom containers, then we'll review model monitoring, which is a service that helps manage the performance of your ML models.
Name:Vertex AI Pipelines
Description:This module discusses Vertex AI pipelines and how to build them to orchestrate your ML workflow.
Name:Best Practices for ML Development
Description:This module reviews best practices for a number of different machine learning processes in Vertex AI.
Name:Course Summary
Description:This module is a summary of the Machine Learning in the Enterprise course.
Name:Series Summary
Description:This module is a summary of the Machine Learning on Google Cloud course series.
This course encompasses a real-world practical approach to the ML Workflow: a case study approach that presents an ML team faced with several ML business requirements and use cases. This team must understand the tools required for data management and governance and consider the best approach for data preprocessing: from providing an overview of Dataflow and Dataprep to using BigQuery for preprocessing tasks. The team is presented with three options to build machine learning models for two specific use cases. This course explains why the team would use AutoML, BigQuery ML, or custom training to achieve their objectives. A deeper dive into custom training is presented in this course. We describe custom training requirements from training code structure, storage, and loading large datasets to exporting a trained model. You will build a custom training machine learning model, which allows you to build a container image with little knowledge of Docker. The case study team examines hyperparameter tuning using Vertex Vizier and how it can be used to improve model performance. To understand more about model improvement, we dive into a bit of theory: we discuss regularization, dealing with sparsity, and many other essential concepts and principles. We end with an overview of prediction and model monitoring and how Vertex AI can be used to manage ML models.
