|
所在平台: Udemy |
课程主页: https://www.udemy.com/course/building-recommendation-engine-with-machine-learning-rag/
课程评论：没有评论
课程名称：《使用机器学习与检索增强生成构建推荐引擎》 课程概述：欢迎参加《使用机器学习与检索增强生成构建推荐引擎》课程。此课程为以项目为基础的系统性学习，您将学习如何利用Tensorflow、Surprise和检索增强生成（RAG）构建智能推荐系统。该课程完美结合了Python和机器学习，是提升编程技能和软件开发技术知识的理想机会。 在介绍环节，您将学习推荐引擎的基本原理，包括其应用案例和技术限制，同时了解如何利用检索增强生成改善推荐系统。接下来的课程部分将逐步介绍推荐引擎的工作原理，内容包括数据收集、数据预处理、特征选择、模型选择、模型训练、模型评估、部署、监控和维护。 此外，您将学习如何从Kaggle下载高质量的数据集。项目阶段，我们将首先构建一个基于TensorFlow的产品推荐引擎，该引擎能够根据用户的浏览和购买历史建议相关产品。此推荐系统能分析用户行为，从中提取有意义的模式，并实时生成个性化的产品推荐，帮助企业增强客户参与度、提高转化率并优化购物体验。 接下来，我们将构建一个使用Surprise的电影推荐引擎，帮助用户发现可能喜欢的电影，基于他们过去的评分和偏好，利用协同过滤技术找出用户与电影之间的相似性，提供高度个性化的推荐。这种方法能提高内容发现率，增加用户参与度，并推动流媒体平台的保留率。 然后，我们还将使用检索增强生成构建音乐推荐引擎，能够提供动态且上下文相关的歌曲推荐，通过结合实时外部知识，增强传统推荐方法，提高建议的准确性和多样性。最后，课程结束前，我们将测试推荐引擎的性能，确保模型优化后，将推荐系统部署到Hugging Face Space，让用户根据初始电影输入，模型能够处理实时数据并基于学习到的模式生成个性化推荐。 在学习过程中，您将探索以下内容： - 推荐引擎的基本原理及其应用、技术限制和RAG的实现 - 推荐引擎的工作流程，包括数据收集、预处理、特征选择、模型训练和部署 - 如何使用Kaggle Hub API下载数据集 - 产品推荐引擎的特征选择和构建方法 - 使用Surprise构建和训练电影推荐引擎的方法 - 使用检索增强生成构建音乐推荐引擎 - 如何创建推荐引擎的用户界面 - 如何在Hugging Face上测试和部署推荐引擎 本课程帮助您从机器学习的角度理解构建推荐引擎的重要性，并掌握构建和实现智能推荐系统的技能。
Welcome to Building Recommendation Engine with Machine Learning & RAG course. This is a comprehensive project based course where you will learn how to build intelligent recommendation systems using Tensorflow, Surprise and Retrieval Augmented Generation. This course is a perfect combination between Python and machine learning, making it an ideal opportunity to level up your programming skills while improving your technical knowledge in software development. In the introduction session, you will learn the basic fundamentals of recommendation engine, such as getting to know its use cases, technical limitations, and also learn how retrieval augmented generation can be used to improve your recommendation system. Then, in the next section, you will learn step by step how a recommendation engine works. This section covers data collection, data preprocessing, feature selection, model selection, model training, model evaluation, deployment, monitoring, and maintenance. Afterward, you will also learn how to find and download datasets from Kaggle, it is a platform that offers many high quality datasets from various industries. Once everything is ready, we will start the project. Firstly, we are going to build a product recommendation engine using TensorFlow, it will have the capability of suggesting relevant products to users based on their browsing and purchase history. This recommendation engine will be able to analyze user behavior, extract meaningful patterns, and generate personalized product recommendations in real time. By implementing this system, businesses can enhance customer engagement, increase conversion rates, and optimize the shopping experience through intelligent suggestions. In the next section, we are going to build a movie recommendation engine using Surprise, which will help users discover films they might enjoy based on their past ratings and preferences. This recommendation engine will utilize collaborative filtering techniques to find similarities between users and movies, delivering highly personalized recommendations. With this approach, we can improve content discovery, keep users engaged, and drive higher retention rates for streaming platforms. Following that, we are also going to build a music recommendation engine using Retrieval Augmented Generation that is able to provide dynamic and context aware song recommendations. This recommendation engine will be able to enhance traditional recommendation methods by incorporating real-time external knowledge, improving the accuracy and diversity of song suggestions. Lastly, at the end of the course, we will conduct testing to evaluate the performance of our recommendation engines. After ensuring optimal model performance, we will deploy the recommendation system to Hugging Face Space, where users can select a few initial movies as input, allowing the model to process real-time data and generate personalized recommendations based on learned patterns and similarities.Before getting into the course, we need to ask this question to ourselves, why should we build a recommendation engine using machine learning? Well, here is my answer, by leveraging machine learning, businesses can offer smarter, more personalized recommendations that keep customers engaged, increase sales, and improve loyalty. Meanwhile, from users perspective, they can benefit from a seamless experience, where they receive valuable recommendations effortlessly, saving time and effort in finding what suits their needs.Below are things that you can expect to learn from this course:Learn the basic fundamentals of recommendation engine, such as getting to know its use cases, technical limitations, and RAG implementation in recommendation systemLearn how recommendation engines work. This section cover, data collection, preprocessing, feature selection, model training, model evaluation, and deploymentLearn how to download dataset using Kaggle Hub APILearn how to perform feature selection for product recommendation engineLearn how to build product recommendation engine using Tensorflow and KerasLearn how to build product recommendation engine using TFIDF Vectorizer and Cosine SimilarityLearn how to perform feature selection for movie recommendation engineLearn how to build movie recommendation engine using SurpriseLearn how to build and train collaborative filtering modelLearn how to build music recommendation engine using retrieval augmented generationLearn how to load RAG model and create Facebook AI Similarity Search indexLearn how to build search based recommendation engine using RAGLearn how to build user interface for recommendation engine using Gradio and StreamlitLearn how to test and deploy recommendation engine on Hugging Face
