THE CATHOLIC UNIVERSITY OF AMERICA
Washington, DC 20064
SEMINAR IN FUNCTIONAL ANALYSIS
AND RELATED AREAS
Wednesday, April 29, 2026
5:15 p.m. - 6:15 p.m. 

 SPEAKER : Gabriel Radich
                    The Catholic University of America

TITLE: Attention to Detail: A Modern Mathematical Approach to Image-based Tasks in AI

ABSTRACT: When people, especially in mainstream media, talk about AI and its potential to ‘reason’ independently, have its own agenda and turn against humanity, oftentimes what they fail to recognize is that AI is simply a complicated probability model comprised of millions of parameters, matrix operations, and convenient mathematical formulas such as softmax. In this talk, I intend to unveil the mathematics that governs the components of the Transformer model, which undergirds ChatGPT. My primary interest is not the Transformer’s impact on ‘understanding’ human language, but rather, it’s impact on teaching machines to ‘see’ like humans, or even better than humans. This has spurred an effort to incorporate AI into remote sensing tasks, such as infrared and visible image fusion. In this talk, I will demonstrate how one would go about defining a neural network (with Transformer Encoder and Decoder) mathematically to be used in these image fusion tasks.

 PLACE:  Aquinas Hall, Room 108. The talk will also be held on Zoom from 5:15 p.m. to 6:15 p.m. (ET). See the information about the corresponding link below.

ORGANIZERS: V. Bogdan (The Catholic University of America), P. Kainen (Georgetown University), R. Kalpathy (The Catholic University of America), and A. Levin (The Catholic University of America).

Tel: 202-319-5221  E-mail:levin@cua.edu

Web page:  https://mathematics.catholic.edu/faculty-and-research/mathematics-seminar/index.html

The talk will be on Zoom as well (from 5:15 p.m. to 6:15 p.m. ET).   The following is the information about the corresponding link.