1 |
What is AI? |
I. How should we define AI? |
Exercise 1: Is this AI or not? |
1 |
What is AI? |
II. Related fields |
Exercise 2: Taxonomy of AI, Exercise 3: Examples of tasks |
1 |
What is AI? |
III. Philosophy of AI |
Exercise 4: Definitions, definitions |
2 |
AI problem solving |
I. Search and problem solving |
Exercise 5: A smaller rowboat, Exercise 6: The Towers of Hanoi |
2 |
AI problem solving |
II. Solving problems with AI |
- |
2 |
AI problem solving |
III. Search and games |
Exercise 7: Why so pessimistic, Max? |
3 |
Real world AI |
I. Odds and probability |
Exercise 8: Probabilistic forecasts, Exercise 9: Odds |
3 |
Real world AI |
II. The Bayes rule |
Exercise 10: Bayes rule (part 1), Exercise 11: Bayes rule (part 2) |
3 |
Real world AI |
III. Naive Bayes classification |
Exercise 12: One word spam filter, Exercise 13: Full spam filter |
4 |
Machine learning |
I. The types of machine learning |
- |
4 |
Machine learning |
II. The nearest neighbor classifier |
Exercise 14: Customers who bought similar products, Exercise 15: Filter Bubbles |
4 |
Machine learning |
III. Regression |
--- |
5 |
Neural networks |
I. Neural network basics |
--- |
5 |
Neural networks |
II. How neural networks are built |
--- |
5 |
Neural networks |
III. Advanced neural network techniques |
--- |
6 |
Implications |
I. About predicting the future |
--- |
6 |
Implications |
II. The societal implications of AI |
--- |
6 |
Implications |
III. Summary |
--- |