Building Recommender Systems with Machine Learning and AI

Course Curriculum

Chapter 1: Getting Started

Lecture 1: Udemy 101: Getting the Most From This Course

Lecture 2: Important note

Lecture 3: Note: Alternate dataset download location

Lecture 4: [Activity] Install Anaconda, course materials, and create movie recommendations!

Lecture 5: Course Roadmap

Lecture 6: What Is a Recommender System?

Lecture 7: Types of Recommenders

Lecture 8: Understanding You through Implicit and Explicit Ratings

Lecture 9: Top-N Recommender Architecture

Lecture 10: [Quiz] Review the basics of recommender systems.

Chapter 2: Introduction to Python [Optional]

Lecture 1: [Activity] The Basics of Python

Lecture 2: Data Structures in Python

Lecture 3: Functions in Python

Lecture 4: [Exercise] Booleans, loops, and a hands-on challenge

Chapter 3: Evaluating Recommender Systems

Lecture 1: Train/Test and Cross Validation

Lecture 2: Accuracy Metrics (RMSE, MAE)

Lecture 3: Top-N Hit Rate – Many Ways

Lecture 4: Coverage, Diversity, and Novelty

Lecture 5: Churn, Responsiveness, and A/B Tests

Lecture 6: [Quiz] Review ways to measure your recommender.

Lecture 7: [Activity] Walkthrough of RecommenderMetrics.py

Lecture 8: [Activity] Walkthrough of TestMetrics.py

Lecture 9: [Activity] Measure the Performance of SVD Recommendations

Chapter 4: A Recommender Engine Framework

Lecture 1: Our Recommender Engine Architecture

Lecture 2: [Activity] Recommender Engine Walkthrough, Part 1

Lecture 3: [Activity] Recommender Engine Walkthrough, Part 2

Lecture 4: [Activity] Review the Results of our Algorithm Evaluation.

Chapter 5: Content-Based Filtering

Lecture 1: Content-Based Recommendations, and the Cosine Similarity Metric

Lecture 2: K-Nearest-Neighbors and Content Recs

Lecture 3: [Activity] Producing and Evaluating Content-Based Movie Recommendations

Lecture 4: A Note on Using Implicit Ratings.

Lecture 5: [Activity] Bleeding Edge Alert! Mise en Scene Recommendations

Lecture 6: [Exercise] Dive Deeper into Content-Based Recommendations

Chapter 6: Neighborhood-Based Collaborative Filtering

Lecture 1: Measuring Similarity, and Sparsity

Lecture 2: Similarity Metrics

Lecture 3: User-based Collaborative Filtering

Lecture 4: [Activity] User-based Collaborative Filtering, Hands-On

Lecture 5: Item-based Collaborative Filtering

Lecture 6: [Activity] Item-based Collaborative Filtering, Hands-On

Lecture 7: [Exercise] Tuning Collaborative Filtering Algorithms

Lecture 8: [Activity] Evaluating Collaborative Filtering Systems Offline

Lecture 9: [Exercise] Measure the Hit Rate of Item-Based Collaborative Filtering

Lecture 10: KNN Recommenders

Lecture 11: [Activity] Running User and Item-Based KNN on MovieLens

Lecture 12: [Exercise] Experiment with different KNN parameters.

Lecture 13: Bleeding Edge Alert! Translation-Based Recommendations

Chapter 7: Matrix Factorization Methods

Lecture 1: Principal Component Analysis (PCA)

Lecture 2: Singular Value Decomposition

Lecture 3: [Activity] Running SVD and SVD++ on MovieLens

Lecture 4: Improving on SVD

Lecture 5: [Exercise] Tune the hyperparameters on SVD

Lecture 6: Bleeding Edge Alert! Sparse Linear Methods (SLIM)

Chapter 8: Introduction to Deep Learning [Optional]

Lecture 1: Deep Learning Introduction

Lecture 2: Deep Learning Pre-Requisites

Lecture 3: History of Artificial Neural Networks

Lecture 4: [Activity] Playing with Tensorflow

Lecture 5: Training Neural Networks

Lecture 6: Tuning Neural Networks

Lecture 7: Activation Functions: More Depth

Lecture 8: Introduction to Tensorflow

Lecture 9: Important Tensorflow setup note!

Lecture 10: [Activity] Handwriting Recognition with Tensorflow, part 1

Lecture 11: [Activity] Handwriting Recognition with Tensorflow, part 2

Lecture 12: Introduction to Keras

Lecture 13: [Activity] Handwriting Recognition with Keras

Lecture 14: Classifier Patterns with Keras

Lecture 15: [Exercise] Predict Political Parties of Politicians with Keras

Lecture 16: Intro to Convolutional Neural Networks (CNN's)

Lecture 17: CNN Architectures

Lecture 18: [Activity] Handwriting Recognition with Convolutional Neural Networks (CNNs)

Lecture 19: Intro to Recurrent Neural Networks (RNN's)

Lecture 20: Training Recurrent Neural Networks

Lecture 21: [Activity] Sentiment Analysis of Movie Reviews using RNN's and Keras

Lecture 22: Tuning Neural Networks

Lecture 23: Neural Network Regularization Techniques

Lecture 24: Generative Adversarial Networks (GAN's)

Lecture 25: GAN's in Action

Lecture 26: [Activity] Generating images of clothing with Generative Adversarial Networks

Chapter 9: Deep Learning for Recommender Systems

Lecture 1: Intro to Deep Learning for Recommenders

Lecture 2: Restricted Boltzmann Machines (RBM's)

Lecture 3: [Activity] Recommendations with RBM's, part 1

Lecture 4: [Activity] Recommendations with RBM's, part 2

Lecture 5: [Activity] Evaluating the RBM Recommender

Lecture 6: [Exercise] Tuning Restricted Boltzmann Machines

Lecture 7: Exercise Results: Tuning a RBM Recommender

Lecture 8: Auto-Encoders for Recommendations: Deep Learning for Recs

Lecture 9: [Activity] Recommendations with Deep Neural Networks

Lecture 10: Clickstream Recommendations with RNN's

Lecture 11: [Exercise] Get GRU4Rec Working on your Desktop

Lecture 12: Exercise Results: GRU4Rec in Action

Lecture 13: Bleeding Edge Alert! Generative Adversarial Networks for Recommendations