|
所在平台: Coursera |
课程主页: https://www.coursera.org/learn/deploying-machine-learning-models
课程评论：没有评论
课程名称：部署机器学习模型 课程概述：在本课程中，我们将学习推荐系统（这是我们将在顶点项目中研究的内容），并探讨数据产品的部署问题。到本课程结束时，您应该能够实现一个有效的推荐系统（例如，预测评分或生成相关产品列表），并理解在实际大规模数据集上部署此类系统所需的工具和技术。本课程是Python数据产品预测分析专业化的最终课程，建立在之前的三门课程的基础上（基本数据处理与可视化、设计思维与数据产品的预测分析，以及有意义的预测建模）。在每个步骤中，您将获得数据处理的实践经验并提升技能，最终以一个涵盖专业化中所有概念的顶点项目收尾。 课程大纲： 第一部分：介绍 - 描述：欢迎来到“部署机器学习模型”的第一周！我们将浏览课程大纲，下载所有课程材料，并让你的系统为课程做好准备。我们还将介绍推荐系统的基础知识，并将其与其他类型的机器学习区分开来。 第二部分：实现推荐系统 - 描述：本周，我们将学习如何实现基于相似性的推荐系统，返回与用户给定项目相似的预测。我们将讨论如何基于梯度下降和杰卡德相似度优化这些模型。 第三部分：部署推荐系统 - 描述：本周，我们将学习Python web服务器框架以及交互式Python数据应用程序的总体结构。我们还将提供一些关于部署和监测应用程序的最佳实践建议。 第四部分：项目4：推荐系统 - 描述：在这个最终项目中，您将构建自己的推荐系统。寻找一个数据集，清理它，并根据数据集创建一个预测系统。这将帮助您为即将到来的顶点项目做好准备，您将利用本专业化中所有课程的技能完成一个整体项目！ 第五部分：顶点项目 - 描述：是时候检验你所有的努力成果了！这个顶点项目由四个部分组成，每个部分都来自于本专业化的不同课程。是时候展示您在本专业化中学到的所有知识了。
Part: 1
Title:Introduction
Description:Welcome to the first week of Deploying Machine Learning Models! We will go over the syllabus, download all course materials, and get your system up and running for the course. We will also introduce the basics of recommender systems and differentiate it from other types of machine learning
Part: 2
Title:Implementing Recommender Systems
Description:This week, we will learn how to implement a similarity-based recommender, returning predictions similar to an user's given item. We will cover how to optimize these models based on gradient descent and Jaccard similarity.
Part: 3
Title:Deploying Recommender Systems
Description:This week, we will learn about Python web server frameworks and the overall structure of interactive Python data applications. We will also cover some tips for best practices on deploying and monitoring your applications.
Part: 4
Title:Project 4: Recommender System
Description:For this final project, you will build a recommender system of your own. Find a dataset, clean it, and create a predictive system from the dataset. This will help prepare you for the upcoming capstone, where you will harness your skills from all courses of this specialization into one single project!
Part: 5
Title:Capstone
Description:Time to put all your hard work to the test! This capstone project consists of four components, each drawing from a separate course in this specialization. It's time to show off everything you've learned from this specialization.
In this course we will learn about Recommender Systems (which we will study for the Capstone project), and also look at deployment issues for data products. By the end of this course, you should be able to implement a working recommender system (e.g. to predict ratings, or generate lists of related products), and you should understand the tools and techniques required to deploy such a working system on real-world, large-scale datasets. This course is the final course in the Python Data Products for Predictive Analytics Specialization, building on the previous three courses (Basic Data Processing and Visualization, Design Thinking and Predictive Analytics for Data Products, and Meaningful Predictive Modeling). At each step in the specialization, you will gain hands-on experience in data manipulation and building your skills, eventually culminating in a capstone project encompassing all the concepts taught in the specialization.
