TDT41 - From Networks to Causal Models in Artificial Intelligence - Kunnskapsbasen
TDT41 - From Networks to Causal Models in Artificial Intelligence
From Networks to Causal Models in Artificial Intelligence
Instructor: Ole Jakob Mengshoel
The collection, storage, and analysis of massive and diverse data is now a well-established fact of life. This dramatic increase in data handling capability is due to technological advances in sensors (including the Internet of Things), smartphones, communication infrastructures, computing hardware, as well software frameworks and libraries.
Data also plays a key role in artificial intelligence (AI) and machine learning (ML). However, the disciplines of AI and ML are as much – if not more – about models as about data. Indeed, popular and well-established methods in AI and ML focus on network models such as neural networks and Bayesian networks (and probabilistic graphical models more broadly). There are, for example, recent impressive advances in deep learning with neural networks.
Another important recent development is the increased emphasis on causality in AI. Clearly, concepts like causality or cause-and-effect are not new and have also been treated – at least to some extent – in disciplines such as econometrics, epidemiology, philosophy, psychology, and statistics. That being said, it appears that the AI perspective brings something new to the study of causality. In this course, students will acquire a deeper understanding of causality along with its application from an AI perspective. Connections will be made to other models and methods within AI as well as to other disciplines. We will structure the course around the recent book “The Book of Why: The New Science of Cause and Effect” by Judea Pearl and Dana Mackenzie. One of the book’s authors, the 2011 Turing Award winner Judea Pearl, is one of the key advocates of causality in AI. In addition to “The Book of Why,” closely related articles and papers will be studied and discussed in the course.
Knowledge: The students will obtain a deeper insight into research questions, concepts, and techniques related to the notion of cause-and-effect in AI, including relationships to other methods and models used in AI. Knowledge will be acquired through studies of theory as well as application examples.
Competence: The students should be able to put the subject into a broader societal, scientific, technical, and business context as a result of taking the course.
This course will be workshop-based. The syllabus is based on and structured according to “The Book of Why” along with a collection of scientific articles and papers. Students will be required to read book chapters and any additional literature prior to the workshops. The workshop will be interactive sessions, with short presentation by students along with open discussions.
An exception to this format is the very first workshop. The first workshop, which will be more of a seminar, will be led by the instructor and will introduce the topics as well as the structure of the course.
Participation in workshops (or seminars) as well as hand-in of an essay or take-home test make up the mandatory activities. The first workshop will be in late-August 2021, and will be on-line. Later workshops will take place on-line or in-person according to the COVID-19 situation at the time. Please see below for dates.
Note: The first meeting is Tuesday 31.8., starting at 10:15, and will take place on-line. If you are registered for the course, you will receive an email with further details about course participation by 16:00 on Monday 30.8. If you do not receive such details despite being registered for the course, or may be interested in taking the course but has not registered (yet), please contact the instructor by email: ole.j.mengshoel at ntnu.no.
Workshops: 30% of final mark.
- Students must participate in all six workshops that make up the course (see below for details)
- Students need to prepare for and actively participate in each workshop
- Each student needs to lead certain discussions of papers and topics in some of the workshops
- When a student is not leading the discussion, it is still expected that the student actively participates
Take-home essay or test: 70% of final mark. The date for the take-home is at the end of the semester, in late-November or early-December, after the final workshop. The date has now been set to Tuesday November 23.
- Workshop 1, Tuesday 31.8., 10:15-12: Introduction “Mind over Data” plus structure and overview of course
- Workshop 2, Tuesday 14.9., 10:15-12: Chapter 1 “The Ladder of Causation,” Chapter 2 “From Buccaneers to Guinea Pigs: The Genesis of Causal Inference” and Chapter 3 “From Evidence to Causes: Reverend Bayes Meets Mr. Holmes” plus related literature
- Workshop 3, Tuesday 28.9., 10:15-12: Chapter 4: “Confounding and Deconfounding: Or, Slaying the Lurking Variable” and Chapter 5 “The Smoke-Filled Debate: Clearing the Air” plus related literature
- Workshop 4, Tuesday 12.10., 10:15-12: Chapter 6 “Paradoxes Galore!” and Chapter 7 “Beyond Adjustment: The Conquest of Mount Intervention” plus related literature
- Workshop 5, Tuesday 26.10., 10:15-12: Chapter 8 “Counterfactuals: Mining Worlds that Could Have Been” and Chapter 9 “Mediation: The Search for a Mechanism” plus related literature
- Workshop 6, Tuesday 9.11., 10:15-12: Chapter 10 “Big Data, Artificial Intelligence, and the Big Questions” plus related literature
The chapter titles above refer to chapters in “The Book of Why: The New Science of Cause and Effect” by Judea Pearl and Dana Mackenzie. The “related literature” will be detailed during and early on in the course, and will in part depend on the backgrounds, interests, and number of students taking the course. Thus there may be some minor adjustments to the course, relative to the above schedule, for Fall 2021.