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 seminar-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 seminars. The seminars will be interactive sessions, with short presentation by students along with open discussions. An exception to this format is the very first seminar. The first seminar will be led by the instructor and will introduce the topic as well as the structure of the course.
Participation in seminars (or workshops). The first seminar will be in late-August or early-September 2020, and will be on-campus (in Trondheim) or on-line according to the COVID-19 situation at the time.
- Seminar 1: Introduction “Mind over Data” plus structure and overview of course
- Seminar 2: Chapter 1 “The Ladder of Causation” and Chapter 2 “From Buccaneers to Guinea Pigs: The Genesis of Causal Inference” plus related literature
- Seminar 3: Chapter 3 “From Evidence to Causes: Reverende Bayes Meets Mr. Holmes” and Chapter 4: “Confounding and Deconfounding: Or, Slaying the Lurking Variable” plus related literature
- Seminar 4: Chapter 5 “The Smoke-Filled Debate: Clearing the Air” and Chapter 6 “Paradoxes Galore!” plus related literature
- Seminar 5: Chapter 7 “Beyond Adjustment: The Conquest of Mount Intervention” and Chapter 8 “Counterfactuals: Mining Worlds that Could Have Been” plus related literature
- Seminar 6: Chapter 9 “Mediation: The Search for a Mechanism” and 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 early on in the course, and will in part depend on the backgrounds, interests, and number of students taking the course.