15-181, New in Spring 2022!
Demystifying Artificial Intelligence
Overview
This course will pull back the curtains on artificial intelligence, helping you learn what it is, what it can do, how to use it, how it works, and what can go wrong. This course is designed for students that want to learn about AI and machine learning but don't have the course schedule bandwidth to build up the math and computing background required for full-fledged intro AI and ML courses, such as 15-281 and 10-301. Leveraging high school algebra and basic Python programming skills from 15-110, we'll help you implement key pieces of AI techniques from the nearest neighbor algorithm to simple neural networks. Through in-class activities, weekly recitations, and course assignments, you'll start to learn how to use AI systems, including how to make them "intelligent", what data might be needed, and what can go wrong. Ethical discussions will be woven throughout the course to enable you to think critically about how AI impacts our society.
Prerequisites
The prequisite for this course is:
- 15-110 Principles of Computing (15-112 is also acceptable)
That's it! Normally, AI and Machine Learning courses require prereqs for probability, linear algebra, calculus, and 15-122. We'll build on 15-110 computing skills and basic high school algebra.
Who should take this course?
This course is particularly good for students that want to learn AI but aren't planning to take the list of AI/ML course prerequisites: 15-122 + probability + linear algebra, etc.
Why this course?
As artificial intelligence technology becomes more pervasive in both everyday products and mainstream media, it is increasingly important that all of us begin to learn about the basic concepts behind AI. While computer science, calculus, linear algebra, and probability prerequisites are required to become an AI developer, students outside of the SCS and STEM majors can learn a myriad of machine learning and AI concepts by simply leveraging the your knowledge of high school algebra and basic programming constructs.
Office Hours
If standing office hours don't work for you, we're happy to do office hours by appointment. See available appointment slots or make a private post on Piazza with a few times that work for you and we'll set something up.
Schedule (subject to change)
| Date | Topic | Slides | Notes/Code |
|---|---|---|---|
| 1/18 Tue | 1: Overview & Intelligence | pptx (inked) pdf (inked) | |
| 1/20 Thu | 2: Five Big Ideas in AI & Agents | pptx (inked) pdf (inked) | |
| 1/25 Tue | 3: Visualizing Simple Data | N/A |
visualizing_data_1.ipynb
visualizing_data_2.ipynb |
| 1/27 Thu | 4: Visualizing Simple Data | N/A | visualizing_data_3.ipynb |
| 2/1 Tue | 5: Nearest Neighbor Classification | pptx (inked) pdf (inked) |
nearest_neighbor_1.ipynb
nearest_neighbor_2.ipynb nearest_neighbor_3.ipynb |
| 2/3 Thu | 6: Data & ML Models | pptx (inked) pdf (inked) | |
| 2/8 Tue | 7: Image Classification | pptx (inked) pdf (inked) | |
| 2/10 Thu | 8: Design Challenges | pptx (inked) pdf (inked) | |
| 2/15 Tue | 9: Linear Regression and Optimization | pptx (inked) pdf (inked) |
regression_interactive.ipynb
regression_1.ipynb regression_blind_optimization.ipynb regression_2_grid_search.ipynb (sol) |
| 2/17 Thu | 10: Linear Regression and Optimization | see prev slides |
regression_3_search_visualization.ipynb
(sol)
gradients.ipynb (sol) (sol N-D) regression_blind_optimization_gradients.ipynb regression_optimization.ipynb (sol) |
| 2/22 Tue | 11: Regression with More Features | see prev slides | coins.ipynb (sol) |
| 2/24 Thu | 12: Regression Applications | pptx (inked) pdf (inked) | |
| 3/1 Tue | 13: Neuron for Non-linear Datasets | pptx (inked) pdf (inked) | |
| 3/3 Thu | 14: Three Neuron Network | see prev slides | |
| 3/8 Tue | No class: Spring Break | ||
| 3/10 Thu | No class: Spring Break | ||
| 3/15 Tue | 15: Neural Network Optimization | pptx (inked) pdf (inked) | |
| 3/17 Thu | 16: Neural Network Structure | pptx (inked) pdf (inked) | |
| 3/22 Tue | 17: Using Neural Networks | see prev slides | |
| 3/24 Thu | 18: Feature Learning: Dimensionality Reduction | pptx (inked) pdf (inked) | |
| 3/29 Tue | 19: Feature Learning: Autoencoders | see prev slides | |
| 3/31 Thu | 20: GANs | pptx (inked) pdf (inked) | |
| 4/5 Tue | 21: GANs | see prev slides | |
| 4/7 Thu | No class: Carnival | ||
| 4/12 Tue | 22: Natural Language Processing | pptx (inked) pdf (inked) | |
| 4/14 Thu | 23: Natural Language Processing | see prev slides | |
| 4/19 Tue | 24: Search Applications | pptx (inked) pdf (inked) | |
| 4/21 Thu | 25: Search Trees | see prev slides | |
| 4/26 Tue | 26: Constraint Satisfaction Problems | see prev slides | |
| 4/28 Thu | 27: Human Compatible AI | pptx (inked) pdf (inked) | |
| 5/3 Tue | FINAL EXAM | Take home exam - 72 hours | 5/3 Tue 5:30 pm - 5/6 Fri 5:30 pm |