Fall semester 2023

Module organizer: Professor Kerstin Bach

Course content and start-up

A selected set of papers (including book chapters) related to case-based reasoning combined with general domain knowledge and other method components will be discussed. The actual focus will to some extent depend on the project and interests of the students taking the course.
The course will be run as a set of seminar meetings in which selected papers are summarized by the students and discussed in the group.
The first seminar meeting will take place on Tuesday September 12 at 13:00, in room 207 (Gamle Fysikk)
In the start-up meeting a general overview of the course will be given, the course material will be presented and discussed, and a scheme for dividing the presentations between the students will be initialized. For this meeting, we expect that the participants have read papers 1.-3. (usually as part of earlier courses) as well as the two papers listed in Seminar 1.
The text for these seminars will be based on the textbook Case-Based Reasoning, by Michael Richter and Rosina Weber (Springer 2013), together with additional papers. The textbook is downloadable for free if you are on the NTNU network, at Springer Link. Several chapters from this book was included in the regular ML+CBR course TDT4173.

It is assumed that the students have a background in CBR corresponding to the CBR part of the AI-2 course (TDT4171) and the ML+CBR course (TDT4173). This means that all participants should - at least - make themselves familiar with the following set of papers before the course starts:

1. A. Aamodt and E. Plaza, 1994: Case-based reasoning; Foundational issues, methodological variations, and system approaches. AI Communications, 7(1), pgs. 39-59.
2. Chapters 2, 3, 6, and 8 in Richter/Weber's Case-Based Reasoning Textbook
3. A. Aamodt: Knowledge-intensive case-based reasoning in Creek. ECCBR 2004. LNAI 3155, Spinger, 2004. pgs. 1-16.

Course structure

We will have four meetings to discuss the set of course papers. The papers will constitute the course "pensum".

As students of this module you are assumed to work with the topics of the respective papers in between the meetings, and to browse the Internet or use other sources to fill in missing details.

You are also encouraged to arrange group meetings among yourselves between the scheduled seminar meetings. In the seminar meetings, each paper will be presented for discussion by one or two students, who will summarize it, point out particular scientific issues of interest, research evaluation method applied (if any), and strong and weak points of the papers.

You all are expected to read the papers in question before each meeting and prepare for the discussions.

Seminars including the list of papers

The seminar plan and a first set of papers will be decided in the first meeting, and the detailed content will be determined as the course develops.

Seminar 1 - The start-up meeting

Time and place: Tuesday September 12 at 13:00, in room 207 (Gamle Fysikk), 13-15, Slides from the seminar

For the first meeting you should read the following two, rather light-weighted, papers, which we will discuss in plenum. Together they provide a broader context for CBR, in general as well as with respect to the important issue of similarity.

• David Aha: The omniprescence of case-based reasoning in science and application. Proceedings of the Seventeenth SGES International Conference on Knowledge Based Systems and Applied Artificial Intelligence, 1998. pp 261-273.
• Edwina Rissland: AI and Similarity. IEEE Intelligent Systems, May/June 2006. pp 39-49.

The continued content of the seminar will include papers on the topic of CBR and explainability. The following list of papers might be extended depending on the number of students attending the course:

Seminar 2 - Explanations

• Smyth, B., Keane, M.T. (2022). A Few Good Counterfactuals: Generating Interpretable, Plausible and Diverse Counterfactual Explanations. In: Keane, M.T., Wiratunga, N. (eds) Case-Based Reasoning Research and Development. ICCBR 2022. Lecture Notes in Computer Science(), vol 13405. Springer, Cham. https://doi.org/10.1007/978-3-031-14923-8_2
• Wijekoon, A., Wiratunga, N., Nkisi-Orji, I., Palihawadana, C., Corsar, D., Martin, K. (2022). How Close Is Too Close? The Role of Feature Attributions in Discovering Counterfactual Explanations. In: Keane, M.T., Wiratunga, N. (eds) Case-Based Reasoning Research and Development. ICCBR 2022. Lecture Notes in Computer Science(), vol 13405. Springer, Cham. https://doi.org/10.1007/978-3-031-14923-8_3

Seminar 3 - Applications

• Chen, C., Li, O., Tao, D., Barnett, A., Rudin, C., & Su, J. K. (2019). This looks like that: deep learning for interpretable image recognition. Advances in neural information processing systems, 32.
• Eisenstadt, V., Langenhan, C., Althoff, KD., Dengel, A. (2020). Improved and Visually Enhanced Case-Based Retrieval of Room Configurations for Assistance in Architectural Design Education. In: Watson, I., Weber, R. (eds) Case-Based Reasoning Research and Development. ICCBR 2020. Lecture Notes in Computer Science(), vol 12311. Springer, Cham.

Seminar 4 - Summary and Exam Q&A

• During this session we can discuss questions from the papers and we'll do one example question on the intro-papers.

Schedule

Exam (oral)

Time and place: November 28 (254 Gamle Fysikk, Kerstin's office)

• At the oral exam, you will get 2-3 questions/topics to talk about (appx. 10 mins. each), from the set of book chapters and papers listed on this page. All chapters and papers are relevant for the oral exam.
• Please arrive 20-30 min early so we can keep the schedule.
• Exam schedule: