К содержимому
learnspaceYOUR NEXT CHAPTER
ПРОСТРАНСТВО ОБУЧЕНИЯ
ГлавнаяКаталог курсовМоё обучениеCoursera

Знания без границ

Учитесь у лучших университетов и компаний мира.

Открыть Coursera
Интеграция
Пространство университета
Моё пространствоСтраница курса
↵
ЯЛичный кабинетСтудент
© 2026 LearnSpaceКаждый день — возможность узнать больше.Помощь
Building Recommender Systems with Machine Learning and AI · LearnSpace
Назад в каталог
courseraАнализ данных

Building Recommender Systems with Machine Learning and AI

Курс от Packt
Средний≈ 17.4 чАнглийский
О курсеНавыкиПрограммаПреподаватели

О курсе

This course features Coursera Coach! A smarter way to learn with interactive, real-time conversations that help you test your knowledge, challenge assumptions, and deepen your understanding as you progress through the course. In this course, you'll explore the inner workings of recommender systems, gaining hands-on experience with Python and various machine learning techniques. Starting with the basics, you'll quickly move to more advanced methods like content-based filtering, collaborative filtering, and matrix factorization. By building real-world systems, you'll develop the skills needed to evaluate and improve recommender system performance. As you advance, you'll dive into deep learning for recommender systems, experimenting with technologies like Restricted Boltzmann Machines (RBM) and Autoencoders. You'll also explore TensorFlow Recommenders and other state-of-the-art approaches for building scalable recommendation engines. This course is designed to help you build, test, and deploy sophisticated recommender systems that can be applied in various industries. This course is ideal for those interested in artificial intelligence, machine learning, and data science, especially those who want to build personalized systems to enhance user experience. It will benefit anyone looking to design, evaluate, and optimize recommendation algorithms, making it an excellent resource for aspiring data scientists, machine learning engineers, and AI specialists.

Навыки, которые вы освоите

Model EvaluationAutoencodersMachine Learning MethodsFraud detectionMachine Learning AlgorithmsApplied Machine LearningDimensionality ReductionModel OptimizationApache SparkPython ProgrammingScalabilityArtificial Intelligence and Machine Learning (AI/ML)TensorflowAWS SageMakerAI PersonalizationArtificial Neural Networks

Программа курса

14 модулей · 144 учебных материалов

01Getting Started9 материалов

Getting Started

Introduction to the Course 'Building Recommender Systems with Machine Learning and AI'ЧтениеInstalling Anaconda, Course Materials, and Creating Movie RecommendationsВидеоFull Course ResourcesЧтениеCourse RoadmapВидео

Учитесь у экспертов

Packt - Course Instructors

Преподаватель курса

Building Recommender Systems with Machine Learning and AI
В каталоге вашей программы

Инвестируйте в себя

Новые знания — в удобное для вас время.

Начать на Coursera

Обучение откроется на Coursera
в новой вкладке

Обучение на Coursera

≈ 17.4 ч

14 модулей

Язык: Английский

Субтитры: Венгерский, Казахский, Испанский

Часть программы вашего университета
What Is a Recommender System?Видео
Types of RecommendersВидео
Understanding the Implicit and Explicit RatingsВидео
Top-N Recommender ArchitectureВидео
Review the Basics of a Recommender SystemВидео
02Introduction to Python5 материалов

Introduction to Python

The Basics of Python (Activity)ВидеоData Structures in PythonВидеоFunctions in PythonВидеоBooleans, Loops, and a Hands-on Challenge (Exercise)ВидеоPython Basics with Lists, Tuples, and DictionariesDIALOGUE
03Evaluating a Recommender System11 материалов

Evaluating a Recommender System

Train/Test and Cross-ValidationВидеоAccuracy Metrics Using Root Mean Squared Error (RMSE) and Mean Absolute Error (MAE)ВидеоTop-N Hit Rate - Many WaysВидеоCoverage, Diversity, and NoveltyВидеоChurn, Responsiveness, and A/B TestsВидеоReviewing Ways to Measure Your Recommender (Quiz)ВидеоWalkthrough of RecommenderMetrics.py (Activity)ВидеоWalkthrough of TestMetrics.py (Activity)ВидеоMeasuring the Performance of Singular Value Decomposition (SVD) Recommendations (Activity)ВидеоEvaluating Recommender Systems with Offline MetricsDIALOGUEAssessment 1Задание
04A Recommender Engine Framework5 материалов

A Recommender Engine Framework

Recommender Engine ArchitectureВидеоRecommender Engine Walkthrough - Part 1 (Activity)ВидеоRecommender Engine Walkthrough - Part 2 (Activity)ВидеоReviewing the Results of Our Algorithm Evaluation (Activity)ВидеоBuilding and Evaluating Custom Recommender Systems Using Surprise LibDIALOGUE
05Content-Based Filtering7 материалов

Content-Based Filtering

Content-Based Recommendations and the Cosine Similarity MetricВидеоK-Nearest-Neighbors (KNN) and Content RecommendationsВидеоProducing and Evaluating Content-Based Movie Recommendations (Activity)ВидеоA Note on Using Implicit RatingsВидеоBleeding Edge Alert! Mise-En-Scene Recommendations (Activity)ВидеоDiving Deep into Content-Based Recommendations (Exercise)ВидеоCosine Similarity for Movie RecommendationsDIALOGUE
06Neighborhood-Based Collaborative Filtering15 материалов

Neighborhood-Based Collaborative Filtering

Measuring Similarity and SparsityВидеоSimilarity MetricsВидеоUser-Based Collaborative FilteringВидеоUser-Based Collaborative Filtering - Hands-On (Activity)ВидеоItem-Based Collaborative FilteringВидеоItem-Based Collaborative Filtering - Hands-On (Activity)ВидеоTuning Collaborative Filtering Algorithms (Exercise)ВидеоEvaluating Collaborative Filtering Systems Offline (Activity)ВидеоMeasuring the Hit Rate of Item-based Collaborative Filtering (Exercise)ВидеоK-Nearest-Neighbor (KNN) RecommendersВидеоRunning User-Based and Item-Based K-Nearest-Neighbor (KNN) on MovieLens Dataset (Activity)ВидеоExperimenting with Different K-Nearest-Neighbor (KNN) Parameters (Exercise)ВидеоBleeding Edge Alert! Translation-Based RecommendationsВидеоUnderstanding Neighborhood Based Collaborative FilteringDIALOGUEAssessment 2Задание
07Matrix Factorization Methods7 материалов

Matrix Factorization Methods

Principal Component Analysis (PCA)ВидеоSingular Value Decomposition (SVD)ВидеоRunning Singular Value Decomposition (SVD) and Singular Value Decomposition (SVD ++) on MovieLens (Activity)ВидеоImproving on Singular Value Decomposition (SVD)ВидеоTuning the Hyperparameters on Singular Value Decomposition (SVD) (Exercise)ВидеоBleeding-Edge Alert! Sparse Linear Methods (SLIM)ВидеоUnderstanding Principal Component Analysis (PCA) in Recommender SystemsDIALOGUE
08Introduction to Deep Learning (Optional)26 материалов

Introduction to Deep Learning (Optional)

Deep Learning IntroductionВидеоDeep Learning PrerequisitesВидеоHistory of Artificial Neural Networks (ANN)Видео(Activity) Playing with TensorFlowВидеоTraining Neural NetworksВидеоTuning Neural Networks (Avoiding Overfitting)ВидеоActivation Functions: More DepthВидеоIntroduction to TensorFlowВидеоHandwriting Recognition with TensorFlow - Part 1 (Activity)ВидеоHandwriting Recognition with TensorFlow - Part 2 (Activity)ВидеоIntroduction to KerasВидеоHandwriting Recognition with Keras (Activity)ВидеоClassifier Patterns with KerasВидеоPredicting Political Parties of Politicians with Keras (Exercise)ВидеоIntroduction to Convolutional Neural Network (CNN)ВидеоConvolutional Neural Network (CNN) ArchitectureВидеоHandwriting Recognition with Convolutional Neural Network (CNN) (Activity)ВидеоIntroduction to Recurrent Neural Networks (RNN)ВидеоTraining Recurrent Neural Networks (RNN)ВидеоSentiment Analysis of Movie Reviews Using Recurrent Neural Networks (RNN) and Keras (Activity)ВидеоTuning Neural NetworksВидеоNeural Network Regularization TechniquesВидеоGenerative Adversarial Networks (GANs)ВидеоGANs in ActionВидеоGenerating Images of Clothing with Generative Adversarial Networks (Activity)ВидеоUnderstanding Neural Networks and Deep Learning BasicsDIALOGUE
09Deep Learning for Recommender Systems21 материалов

Deep Learning for Recommender Systems

Introduction to Deep Learning for RecommendersВидеоRestricted Boltzmann Machine (RBM)ВидеоRecommendations with Restricted Boltzmann Machine (RBM) - Part 1 (Activity)ВидеоRecommendations with Restricted Boltzmann Machine (RBM) - Part 2 (Activity)ВидеоEvaluating the Restricted Boltzmann Machine (RBM) Recommender (Activity)ВидеоTuning Restricted Boltzmann Machine (RBM) (Exercise)ВидеоExercise Results: Tuning a Restricted Boltzmann Machine (RBM) RecommenderВидеоAuto-Encoders for Recommendations: Deep Learning for RecommendationВидеоRecommendations with Deep Neural Networks (Activity)ВидеоClickstream Recommendations with Recurrent Neural Networks (RNN)ВидеоGetting GRU4Rec to Work on Your Desktop (Exercise)ВидеоExercise Results: GRU4Rec in ActionВидеоBleeding Edge Alert! Generative Adversarial Networks for RecommendationsВидеоTensorFlow Recommenders (TFRS): Introduction and Building a Retrieval StageВидеоTensorFlow Recommenders (TFRS): Building a Ranking StageВидеоTensorFlow Recommenders (TFRS): Incorporating Side Features and Deep RetrievalВидеоTensorFlow Recommenders (TFRS): Multi-Task Recommenders, Deep and Cross Networks, ScaNN, and ServingВидеоBleeding Edge Alert! Deep Factorization MachinesВидеоMore Emerging Tech to WatchВидеоApplying Neural Networks to Recommender SystemsDIALOGUEAssessment 3Задание
10Scaling It Up12 материалов

Scaling It Up

Introduction and Installation of Apache Spark (Activity)ВидеоApache Spark ArchitectureВидеоMovie Recommendations with Spark, Matrix Factorization, and Alternating Least Squares (ALS) (Activity)ВидеоRecommendations from 20 Million Ratings with Spark (Activity)ВидеоAmazon Deep Scalable Sparse Tensor Network Engine (DSSTNE)ВидеоAmazon Deep Scalable Sparse Tensor Network Engine (DSSTNE) in ActionВидеоScaling Up Amazon Deep Scalable Sparse Tensor Network Engine (DSSTNE)ВидеоAmazon Web Services (AWS) SageMaker and Factorization MachinesВидеоAmazon SageMaker in Action: Factorization Machines on One Million Ratings in the CloudВидеоOther Systems of Note (Amazon Personalize, RichRelevance, Recombee, and More)ВидеоRecommender System ArchitectureВидеоScaling Recommender Systems with Apache SparkDIALOGUE
11Real-World Challenges of Recommender Systems13 материалов

Real-World Challenges of Recommender Systems

The Cold Start Problem (and Solutions)ВидеоImplementing Random Exploration (Exercise)ВидеоExercise Solution - Random ExplorationВидеоStoplistsВидеоImplementing a Stoplist (Exercise)ВидеоExercise Solution - Implementing a StoplistВидеоFiltering Bubbles, Trust, and OutliersВидеоIdentifying and Eliminating Outlier Users (Exercise)ВидеоExercise Solution: Outlier RemovalВидеоFraud, the Perils of Clickstream, and International ConcernsВидеоTemporal Effects and Value-Aware RecommendationsВидеоAddressing the Cold Start Problem in Recommender SystemsDIALOGUEAssessment 4Задание
12Case Studies5 материалов

Case Studies

Exploring YouTube's Recommendation System: Challenges and Deep Learning SolutionsВидеоHow YouTube Uses Deep Learning to Rank and Recommend VideosВидеоHow Netflix Uses Hybrid Algorithms to Power Personalized RecommendationsВидеоHow Netflix Uses Context and Machine Learning to Refine RecommendationsВидеоUnderstanding Recommender Systems: YouTube and Netflix Case StudiesDIALOGUE
13Hybrid Approaches4 материалов

Hybrid Approaches

Hybrid Recommenders and ExerciseВидеоExercise Solution: Hybrid RecommendersВидеоImplementing Hybrid Recommender SystemsDIALOGUEAssessment 5Задание
14Wrapping Up4 материалов

Wrapping Up

More to ExploreВидеоConclusion to the Course 'Building Recommender Systems with Machine Learning and AI'ЧтениеFull Course Practice AssessmentЗаданиеFull Course AssessmentЗадание