80-820 Seminar on Philosophy of Science

12 units, Carnegie Mellon University

In the past 25 years there has been a great deal of research in Machine Learning, Statistics, and Philosophy on inferring graphical causal models from both experimental and nonexperimental data, under a variety of different background assumptions. The goals of this course are i to give students enough background to be able to read, understand, and contribute to the current literature on topics in the representation, use of, and inferences about causal graphs of various kinds ii to relate the current computer sciencestatistics literature on causation to the philosophical literature on related topics. The broad topics of the course will be 1. How to use various kinds of graphs for representation of probabilities, causal models, actual causation, and counterfactuals 2. How to use graphs to answer questions about conditional probabilities, the effects of manipulations, and counterfactuals. 3. Assumptions relating probabilities to causation.

Prerequisites: none listed

Courseweave needs JavaScript to show sections, workloads and planning tools.