The course will be centered around exploring methodological and system-focused perspectives on designing AI systems for education and analyzing educational data using AI methods.
The course will start with a general introduction to AI, where we will cover supervised and unsupervised learning techniques (e.g.,classification and regression models, feature selection and preprocessing of data, clustering, dimensionality reduction and text mining techniques) with a focus on application of these techniques in educational data mining.
After the introduction of the basic methodologies, we will continue with the most relevant applications of AI in educational technologies (e.g., intelligent tutoring and student personalization, scaffolding open-ended discovery learning, socially-aware AI and learning at scale with AI systems). In the final part of the course, we will cover challenges associated with using AI in student facing settings.
Students will be expected to
This is a research driven, hands-on class. Your participation is important.
The final assessment will be a combination of classroom participation, graded exercises, research paper presentation and the project. There will be 3 exercise sets which will be a mix of theoretical and implementation problems. Exercises will be released roughly every 4 weeks, and will total to 40% of your grade. Classroom participation (writing class presentation summaries and discussion forum participation) will account for 20% of the grade. Research paper presentation will account for 10% of the grade and the project will account of the rest of the grade (30%). There will be no written exams.
Lectures: Thu 16:15-18:00 Zoom link (see Moodle)
Discussion Sections: Thu 18:15-19:00 Same zoom link
Discussion forum: Moodle
Textbooks: We will not follow any particular textbook. We will draw material from a number of research papers.
15.09.21 Class website is online!
| Lecture | Date | Topic | Course Materials | Events |
| 1 | 23.09.21 | Introduction | ||
| 2 | 30.09.21 | Prediction | ||
| 3 | 07.10.21 | Structure Discovery and Visualization |
||
| 4 | 14.10.21 | Relationship mining (Correlation and Causal Relationship Mining) |
Assignment 1 out | |
| 5 | 21.10.21 | Content curation | ||
| 6 | 28.10.21 | Automated assessment and error correction Guest lecture by Jill Burstein (Duolingo) |
||
| 7 | 04.11.21 | Language learning Guest lecture by Pedro Caldeira (ETH Zurich) |
Assignment 1 due | |
| 8 | 11.11.21 | Learner modeling | Project Proposal due Assignment 2 out |
|
| 9 | 18.11.21 | Dialog based tutoring | ||
| 10 | 25.11.21 | Scaffolding discovery Guest lecture by Manu Kapur (ETH Zurich) |
||
| 11 | 02.12.21 | Dynamic A/B testing | Assignment 2 due | |
| 12 | 09.12.21 | Computing Literacy Guest lecture by Matti Tedre and Henriikka Vartiainen (Univ. Eastern Finland) |
Assignment 3 out | |
| 13 | 16.12.21 | Socially/culturally-aware AIED Guest lecture by Justine Cassell (INRIA and CMU) |
||
| 14 | 23.12.21 | Ethical issues in AIED |
Assignment 3 is due on 30.12.21. Final project submission (report, code) is due on 23.01.22.
Presentation for 15 minutes followed by a 10-minute question answers/discussion. Please see Moodle for more details.
The goal is to explore an interesting problem in AIED in the context of a real-world data set. If you have a theoretical project, come chat with us. Projects should be done in teams of three students.
You can ask questions on Moodle. Please post questions there, so others can see them and share in the discussion. If you have questions which are not of general interest, please don’t hesitate to contact us directly.
| Lecturers | Mrinmaya Sachan, Tanmay Sinha |
| Teaching Assistants | Kumar Shridhar, Jakub Macina, Josephine Yates, Mian Zhong |