Introduction to Machine Learning
Course Overview
Discover how computers learn from experience in this 25-lecture course by Professor Michael L. Littman. Master Python-based machine learning applications from recommender systems to deep neural networks, while exploring ethical implications of AI.
Video Lessons
Foundations
- Telling the Computer What We Want (31 min)
Overview of machine learning history and medical diagnosis applications - Starting with Python Notebooks and Colab (17 min)
Setup guide for browser-based Python programming
Core Algorithms
- Decision Trees for Logical Rules (31 min)
Building predictive models for spelling patterns and diabetes risk - Neural Networks for Perceptual Rules (30 min)
Image/audio processing comparisons between decision trees and neural nets - Opening the Black Box of a Neural Network (29 min)
Python implementation of neural networks for green screen effects
Statistical Approaches
- Bayesian Models for Probability Prediction (29 min)
Naïve Bayes applications in spam filtering - Genetic Algorithms for Evolved Rules (28 min)
Evolutionary approaches to optimization problems - Nearest Neighbors for Using Similarity (29 min)
Comfort prediction and malware detection systems
Practical Challenges
- The Fundamental Pitfall of Overfitting (28 min)
Avoiding model bias in diabetes dataset analysis - Pitfalls in Applying Machine Learning (28 min)
Case studies in medical and legal data misinterpretation
Advanced Techniques
- Clustering and Semi-Supervised Learning (27 min)
Combining labeled/unlabeled data strategies - Recommendations with Three Types of Learning (30 min)
Conference paper review and Netflix prize case studies - Games with Reinforcement Learning (30 min)
AI strategies for Othello, chess, and Go
Deep Learning
- Deep Learning for Computer Vision (27 min)
ImageNet challenge and object recognition systems - Getting a Deep Learner Back on Track (30 min)
Debugging animal classification neural networks
Language Processing
- Text Categorization with Words as Vectors (30 min)
Word embeddings and spelling correction systems - Deep Networks That Output Language (29 min)
Machine translation and story generation
Creative Applications
- Making Stylistic Images with Deep Networks (29 min)
Dual-stage creative processes in image generation - Making Photorealistic Images with GANs (30 min)
Generative adversarial networks for image manipulation
Emerging Frontiers
- Deep Learning for Speech Recognition (30 min)
Evolution of voice interaction systems - Inverse Reinforcement Learning from People (29 min)
Behavioral prediction algorithms - Causal Inference Comes to Machine Learning (30 min)
Moving beyond correlation to causation
Future Directions
- The Unexpected Power of Over-Parameterization (30 min)
2015 deep-learning breakthroughs - Protecting Privacy within Machine Learning (31 min)
Data anonymization challenges and solutions - Mastering the Machine Learning Process (34 min)
Meta-learning and the future of AI

