Unsupervised Learning, Recommenders, Reinforcement Learning
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.
Monthly Subscription Starting at AED 99 + VAT
- Level Foundation
- Duration 28 hours
- Course by DeepLearning.AI
-
Offered by
About
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.Modules
Welcome to the course!
-
1
Videos
-
1
Readings
1
Videos
- Welcome!
1
Readings
- [IMPORTANT] Have questions, issues or ideas? Join our Forum!
Clustering
-
6
Videos
6
Videos
- What is clustering?
- K-means intuition
- K-means algorithm
- Optimization objective
- Initializing K-means
- Choosing the number of clusters
Practice Quiz: Clustering
-
1
Assignment
1
Assignment
- Clustering
Practice Lab 1
-
1
Programming
- k-means
Anomaly detection
-
6
Videos
6
Videos
- Finding unusual events
- Gaussian (normal) distribution
- Anomaly detection algorithm
- Developing and evaluating an anomaly detection system
- Anomaly detection vs. supervised learning
- Choosing what features to use
Practice quiz: Anomaly detection
-
1
Assignment
1
Assignment
- Anomaly detection
Practice Lab 2
-
1
Programming
- Anomaly Detection
Collaborative filtering
-
4
Videos
4
Videos
- Making recommendations
- Using per-item features
- Collaborative filtering algorithm
- Binary labels: favs, likes and clicks
Practice quiz: Collaborative filtering
-
1
Assignment
1
Assignment
- Collaborative Filtering
Recommender systems implementation detail
-
3
Videos
3
Videos
- Mean normalization
- TensorFlow implementation of collaborative filtering
- Finding related items
Practice lab 1
-
1
Programming
- Collaborative Filtering Recommender Systems
Practice quiz: Recommender systems implementation
-
1
Assignment
1
Assignment
- Recommender systems implementation
Content-based filtering
-
5
Videos
5
Videos
- Collaborative filtering vs Content-based filtering
- Deep learning for content-based filtering
- Recommending from a large catalogue
- Ethical use of recommender systems
- TensorFlow implementation of content-based filtering
Practice Quiz: Content-based filtering
-
1
Assignment
1
Assignment
- Content-based filtering
Practice lab 2
-
1
Programming
- Deep Learning for Content-Based Filtering
Principal Component Analysis
-
3
Videos
-
1
Lab
1
Labs
- PCA and data visualization (optional)
3
Videos
- Reducing the number of features (optional)
- PCA algorithm (optional)
- PCA in code (optional)
Reinforcement learning introduction
-
5
Videos
5
Videos
- What is Reinforcement Learning?
- Mars rover example
- The Return in reinforcement learning
- Making decisions: Policies in reinforcement learning
- Review of key concepts
Practice quiz: Reinforcement learning introduction
-
1
Assignment
1
Assignment
- Reinforcement learning introduction
State-action value function
-
4
Videos
-
1
Lab
1
Labs
- State-action value function (optional lab)
4
Videos
- State-action value function definition
- State-action value function example
- Bellman Equation
- Random (stochastic) environment (Optional)
Quiz: State-action value function
-
1
Assignment
1
Assignment
- State-action value function
Continuous state spaces
-
7
Videos
7
Videos
- Example of continuous state space applications
- Lunar lander
- Learning the state-value function
- Algorithm refinement: Improved neural network architecture
- Algorithm refinement: ϵ-greedy policy
- Algorithm refinement: Mini-batch and soft updates (optional)
- The state of reinforcement learning
Quiz: Continuous state spaces
-
1
Assignment
1
Assignment
- Continuous state spaces
End of Access to Lab Notebooks
-
1
Readings
1
Readings
- [IMPORTANT] Reminder about end of access to Lab Notebooks
Practice Lab: Reinforcement Learning
-
1
Programming
- Reinforcement Learning
Summary and thank you
-
1
Videos
1
Videos
- Summary and thank you
Conversations with Andrew (Optional)
-
1
Videos
1
Videos
- Andrew Ng and Chelsea Finn on AI and Robotics
Acknowledgments
-
2
Readings
2
Readings
- Acknowledgments
- (Optional) Opportunity to Mentor Other Learners
Auto Summary
Discover the "Unsupervised Learning, Recommenders, Reinforcement Learning" course, part of the Machine Learning Specialization by Andrew Ng, offered through Coursera. Focused on data science and AI, this beginner-friendly course covers unsupervised learning, recommender systems, and deep reinforcement learning. With 1680 minutes of content, learners can choose from Starter or Professional subscription options. Ideal for those looking to break into AI or advance their machine learning career.
Andrew Ng
Aarti Bagul
Geoff Ladwig