Machine Learning is a science of getting machines to learn, more specifically, designing algorithms that allow computers to learn from empirical data. In the past decade, Machine Learning has successfully made computers to recognize speeches and hand-written characters, to convert spoken words to text, to effectively understanding and generating human language. In this class, you will learn the most important and up-to-date machine learning techniques, not only the theoretical foundations of these techniques, but also the practice implementation of them. The main topics cover the key questions such as what could be learned by an ML model? what are the factors affecting machine learning model? how to address these training challenges? how have LLMs extended the capabilities of machine learning models and how have they been trained under the schema of reinforcement learning, as well as the future of machine learning in advancing Artificial General Intelligence (AGI).
Class time and location: Tuesday/Thursday 9:30am-10:45am in DeBartolo Hall 244 (1/12 to 4/29)
Office Hours: Prof. Xiangliang Zhang, xzhang33@nd.edu, 354 Fitzpatrick Hall. Tuesdays from 1:00 PM to 2:00 PM, or by appointment.
TA: Weijiang Li wli27@nd.edu; Yujun Zhou yzhou25@nd.edu Wednesday/Fridays 2-3 pm, 150B..
Assignment and Grading:
| Homework | Mid-term exam | Final exam |
| 70% | 15% | 15% |
Numeric grades are computed as percentages, and correspond to letter grades as follows:
| 87≤B+<90% | 77≤C+<80% | 67≤D+<70% | F<60% | |
| 94≤A≤100% | 84≤B<87% | 74≤C<77% | 64≤D<67% | |
| 90≤A-<94% | 80≤B-<84% | 70≤C-<74% | 60≤D-<64% |
There will be regular homework assignments, in the forms of reading and questions-answering, math derivation, implementation of machine learning models. Details of the assignments will be provided later. All assignments must be completed individually. The implementation codes and reports (.ipynb file) should be submitted to Canvas prior to the due date. There are no late submissions, and no partial credit will be given if the submission is after the due date. Any extensions must require extenuating circumstances or a priori negotiation. In principle, each one can at most have an extension to only one submission. Inquiries about grades must be made in writing within one week after they are posted. No exceptions. ChatGPT or other AI generative models should not be used for completing assignments, unless their use is explicitly permitted in the assignment instructions. More details can be found in the course syllabus.
Course Schedule: