DeepLearning.AI - Unsupervised Learning, Recommenders, Reinforcement Learning
- Offered byCoursera
- Public/Government Institute
Unsupervised Learning, Recommenders, Reinforcement Learning at Coursera Overview
Duration | 27 hours |
Total fee | Free |
Mode of learning | Online |
Difficulty level | Beginner |
Official Website | Explore Free Course  |
Credential | Certificate |
- Overview
- Highlights
- Course Details
- Curriculum
Unsupervised Learning, Recommenders, Reinforcement Learning at Coursera Highlights
- Earn a Certificate upon completion
Unsupervised Learning, Recommenders, Reinforcement Learning at Coursera Course details
- 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
- 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
- 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
Unsupervised Learning, Recommenders, Reinforcement Learning at Coursera Curriculum
Unsupervised learning
Welcome!
What is clustering?
K-means intuition
K-means algorithm
Optimization objective
Initializing K-means
Choosing the number of clusters
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
Clustering
Anomaly detection
Recommender systems
Making recommendations
Using per-item features
Collaborative filtering algorithm
Binary labels: favs, likes and clicks
Mean normalization
TensorFlow implementation of collaborative filtering
Finding related items
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
Collaborative Filtering
Recommender systems implementation
Content-based filtering
Reinforcement learning
What is Reinforcement Learning?
Mars rover example
The Return in reinforcement learning
Making decisions: Policies in reinforcement learning
Review of key concepts
State-action value function definition
State-action value function example
Bellman Equations
Random (stochastic) environment (Optional)
Example of continuous state space applications
Lunar lander
Learning the state-value function
Algorithm refinement: Improved neural network architecture
Algorithm refinement: e-greedy policy
Algorithm refinement: Mini-batch and soft updates (optional)
The state of reinforcement learning
Summary and thank you
Acknowledgments
Reinforcement learning introduction
State-action value function
Continuous state spaces
Other courses offered by Coursera
Student Forum
Anything you would want to ask experts?