Understanding causality is arguably the ultimate goal in any field of science. Knowledge about causality allows one to predict a system’s behavior under external interventions, a key step towards understanding and engineering that system. While the gold standard for establishing causality remains controlled experimentation, such experimentation is not always possible due to practical or ethical concerns. Inferring causality from observational data thus has become an increasingly popular area of study, attracting researchers from statistics, philosophy, machine learning, artificial intelligence, and data science. The ever-changing field of causal discovery makes for a steep learning curve for students and junior researchers. This conference aims to provide a deep review of causal discovery to help orient researchers new to the topic.
For conference slides click HERE
The conference lectures will focus on the latest developments on the theory and applications of deep learning, bridging models and algorithms from two different fields: (1) machine learning, including logistic regression and deep neural networks; and, (2) numerical PDEs, including finite element and multigrid methods. The lecture series will build upon a discussion of the latest developments in machine learning models and algorithms, and will present cutting-edge research on intrinsically connected topics. It is expected that this conference will bring novel insights into the understanding of deep learning, and further promote their analysis and applications in different scientific and engineering fields.
For Conference Zoom sessions and slides, click here
These conferences are intended to stimulate interest and activity in mathematical research. Each five day conference features a distinguished lecturer or team of lecturers delivering ten lectures on a topic of important current research in one sharply focused area of the mathematical sciences.
The lecturer or lecturers prepare extensive online materials that are made available at https://www.cbmsweb.org/regional-conferences/past-conferences/. They are also expected to prepare an expository monograph based upon these lectures, which is normally published as a part of a regional conference series.
Depending upon the conference topic, the monograph is published by the American Mathematical Society, the Society for Industrial and Applied Mathematics, or jointly by the American Statistical Association and the Institute of Mathematical Statistics.
Support for about 30 participants is provided and the conference organizer invites both established researchers and interested newcomers, including postdoctoral fellows and graduate students, to attend. Information about an individual conference may be obtained by contacting the conference organizer.