Decoding Neural Networks: A New Frontier in Astrophysical Discovery - Brice Menard - 11/06/2024

This is a high-level research talk designed for professional astronomers. It is part of the Caltech Astronomy TAPIR seminar series, roughly hour-long presentations given by top scientists from around the world to the members of our department. All are welcome to watch these presentations; however, for talks specifically designed for the general public, please see our Caltech Astro Outreach channel: https://youtube.com/c/caltechastro

Date: 11/06/2024
Speaker: Brice Menard - Professor, Department of Physics and Astronomy, Johns Hopkins University
Title: Decoding Neural Networks: A New Frontier in Astrophysical Discovery
Abstract:
Artificial Intelligence is transforming science at many levels. Neural networks have changed the ways we interact with data and how we think about statistics. What is fundamentally different? What can we expect to learn from them? Do they have to be opaque? This talk will demystify the "black box" of neural networks by examining their fundamental learning mechanisms and internal representations. I will show how to reveal their encoded features and how to compare networks trained on different datasets. I will then discuss how to use them for astrophysical explorations while maintaining the level of control of more traditional approaches.

Видео Decoding Neural Networks: A New Frontier in Astrophysical Discovery - Brice Menard - 11/06/2024 канала Caltech Astro Seminars