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
Unsupervised Learning, Recommenders, Reinforcement Learning · LearnSpace
Назад в каталог
courseraАнализ данных

Unsupervised Learning, Recommenders, Reinforcement Learning

Курс от DeepLearning.AI, Stanford Online
Начальный≈ 27.9 чАнглийский
О курсеНавыкиПрограммаПреподаватели

О курсе

In the third course of the Machine Learning Specialization, you will: • Use unsupervised learning techniques for unsupervised learning: including clustering and anomaly detection. • Build recommender systems with a collaborative filtering approach and a content-based deep learning method. • Build a deep reinforcement learning model. The Machine Learning Specialization is a foundational online program created in collaboration between DeepLearning.AI and Stanford Online. In this beginner-friendly program, you will learn the fundamentals of machine learning and how to use these techniques to build real-world AI applications. This Specialization is taught by Andrew Ng, an AI visionary who has led critical research at Stanford University and groundbreaking work at Google Brain, Baidu, and Landing.AI to advance the AI field. This 3-course Specialization is an updated and expanded version of Andrew’s pioneering Machine Learning course, rated 4.9 out of 5 and taken by over 4.8 million learners since it launched in 2012. It provides a broad introduction to modern machine learning, including supervised learning (multiple linear regression, logistic regression, neural networks, and decision trees), unsupervised learning (clustering, dimensionality reduction, recommender systems), and some of the best practices used in Silicon Valley for artificial intelligence and machine learning innovation (evaluating and tuning models, taking a data-centric approach to improving performance, and more.) By the end of this Specialization, you will have mastered key concepts and gained the practical know-how to quickly and powerfully apply machine learning to challenging real-world problems. If you’re looking to break into AI or build a career in machine learning, the new Machine Learning Specialization is the best place to start.

Навыки, которые вы освоите

Reinforcement LearningAnomaly DetectionUnsupervised LearningArtificial Neural NetworksSupervised LearningDeep LearningData EthicsArtificial IntelligenceDimensionality ReductionApplied Machine LearningMachine LearningResponsible AI

Программа курса

3 модулей · 65 учебных материалов

01Unsupervised learning18 материалов

Welcome to the course!

Welcome!ВидеоJoin the DeepLearning.AI Forum to ask questions, get support, or share amazing ideas!Чтение

Clustering

What is clustering?ВидеоK-means intuitionВидео

Учитесь у экспертов

Andrew Ng

Instructor

Aarti Bagul

Curriculum Engineer

Geoff Ladwig

Curriculum Engineer

Eddy Shyu

Instructor

Unsupervised Learning, Recommenders, Reinforcement Learning
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

≈ 27.9 ч

3 модулей

Язык: Английский

Субтитры: Китайский (Тайвань), Арабский, Французский, Бенгальский, Узбекский, Украинский, Китайский (Китай), Греческий, Итальянский, Бразильский португальский, Вьетнамский, Нидерландский, Корейский, Немецкий, Пушту, Урду, Русский, Тайский, Индонезийский, Шведский, Турецкий, Азербайджанский, Испанский, Дари, Хинди, Японский, Финский, Казахский, Малайский, Венгерский, Польский

Часть программы вашего университета
K-means algorithmВидео
Optimization objectiveВидео
Initializing K-meansВидео
Choosing the number of clustersВидео

Practice Quiz: Clustering

ClusteringЗадание

Practice Lab 1

k-meansПрограммирование

Anomaly detection

Finding unusual eventsВидеоGaussian (normal) distributionВидеоAnomaly detection algorithmВидеоDeveloping and evaluating an anomaly detection systemВидеоAnomaly detection vs. supervised learningВидеоChoosing what features to useВидео

Practice quiz: Anomaly detection

Anomaly detectionЗадание

Practice Lab 2

Anomaly DetectionПрограммирование
02Recommender systems21 материалов

Collaborative filtering

Making recommendationsВидеоUsing per-item featuresВидеоCollaborative filtering algorithmВидеоBinary labels: favs, likes and clicksВидео

Practice quiz: Collaborative filtering

Collaborative FilteringЗадание

Recommender systems implementation detail

Mean normalizationВидеоTensorFlow implementation of collaborative filteringВидеоFinding related itemsВидео

Practice lab 1

Collaborative Filtering Recommender SystemsПрограммирование

Practice quiz: Recommender systems implementation

Recommender systems implementationЗадание

Content-based filtering

Collaborative filtering vs Content-based filteringВидеоDeep learning for content-based filteringВидеоRecommending from a large catalogueВидеоEthical use of recommender systemsВидеоTensorFlow implementation of content-based filteringВидео

Practice Quiz: Content-based filtering

Content-based filteringЗадание

Practice lab 2

Deep Learning for Content-Based FilteringПрограммирование

Principal Component Analysis

Reducing the number of features (optional)ВидеоPCA algorithm (optional)ВидеоPCA in code (optional)ВидеоPCA and data visualization (optional)Лабораторная
03Reinforcement learning26 материалов

Reinforcement learning introduction

What is Reinforcement Learning?ВидеоMars rover exampleВидеоThe Return in reinforcement learningВидеоMaking decisions: Policies in reinforcement learningВидеоReview of key conceptsВидео

Practice quiz: Reinforcement learning introduction

Reinforcement learning introductionЗадание

State-action value function

State-action value function definitionВидеоState-action value function exampleВидеоState-action value function (optional lab)ЛабораторнаяBellman EquationВидеоRandom (stochastic) environment (Optional)Видео

Quiz: State-action value function

State-action value functionЗадание

Continuous state spaces

Example of continuous state space applicationsВидеоLunar landerВидеоLearning the state-value functionВидеоAlgorithm refinement: Improved neural network architectureВидеоAlgorithm refinement: ϵ-greedy policyВидеоAlgorithm refinement: Mini-batch and soft updates (optional)Видео

Quiz: Continuous state spaces

Continuous state spacesЗадание

End of Access to Lab Notebooks

[IMPORTANT] Reminder about end of access to Lab NotebooksЧтение

Practice Lab: Reinforcement Learning

Reinforcement LearningПрограммирование

Summary and thank you

Summary and thank youВидео

Conversations with Andrew (Optional)

Andrew Ng and Chelsea Finn on AI and RoboticsВидео

Acknowledgments

AcknowledgmentsЧтение(Optional) Opportunity to Mentor Other LearnersЧтение
The state of reinforcement learningВидео