CSC 480/580: Principles of Machine Learning (Spring 2024)
Machine learning is about automatic ways for computers to collect and/or adapt to data to make predictions, make decisions, or gain insight. It can also be seen as a fundamentally different way of writing computer programs from traditional programming, which is often an attractive way of solving practical problems. Students will learn the fundamental frameworks, computational methods, and algorithms that underlie current machine learning practice, and how to derive and implement many of them. They will also learn both advantages and unique risks that this approach offers.
Logistics info
Time and venue: TuTh 9:30am-10:45am, Gould-Simpson 906
Piazza link; Access Code: 285esihd06d
Gradescope: 480 entry code: B2DGGG, 580 entry code: NPNZZ5
We will be using Piazza to make important announcements and do Q&As. Some general rules:
- If you have technical questions, try posing your questions as general as possible, to promote discussions among the class.
- We will not answer private Piazza posts that seek to check the correctness of (partial) solutions. You are welcome to come to office hours to discuss them.
Instructor
Gould-Simpson 720
Office Hour: TBD
Textbook
The required textbook is Hal Daumé’s A Course in Machine Learning, freely available online.
We recommended the following texts for optional reading:
Moritz Hardt and Benjamin Recht, Patterns, predictions, and actions: Foundations of machine learning
Ian Goodfellow, Yoshua Bengio, and Aaron Courville, Deep Learning
Shai Shalev-Shwartz and Shai Ben-David, Understanding machine learning: from theory to algorithms
Trevor Hastie, Robert Tibshirani, and Jerome Friedman, The elements of statistical learning (2nd edition).
Tom Mitchell, Machine Learning.
Kevin Murphy, Machine learning: a probabilistic perspective.
Richard Duda, Peter Hart, and David Stork, Pattern classification (2nd edition).
Review for prerequisites
Here are some excellent notes for probability review and linear algebra review from Stanford’s CS 229 course.
See also The matrix cookbook, The Probability and Statistics Cookbook, and Calculus cheatsheet (recommended by Prof. Kwang-Sung Jun).
LaTeX
You may find using LaTeX helpful in writing homeworks or reports. Some useful LaTeX resources: Learn LaTeX in 30 minutes by Overleaf; Introduction to LaTeX by MIT Research Science Institute
Generative AI use
In this course, generative artificial intelligence/large-language-models tools, such as ChatGPT, Dall-e, Bard, Bing, may be used for assignments with appropriate acknowledgment and citation. However, the use of LLMs is only limited to polishing and refining, not for generating entire pieces of writing. All submitted assignments must be the original work of the student. Specifically, you are responsible for checking facts, finding reliable sources for, and making a careful, critical examination of any work that you submit; you should be comfortable to explain any information in your submission.
If you are in doubt as to whether you are using generative AI tools appropriately in this course, I encourage you to discuss your situation with me. Be aware that many AI companies collect information; do not enter confidential information as part of a prompt. LLMs may make up or hallucinate information. These tools may reflect misconceptions and biases of the data on which they were trained and the human-written prompts used to steer them.