A Conceptual Introduction to Deep Learning

Add to your list(s) Download to your calendar using vCal

• Joshua Speagle (Univ. of Toronto)
• Monday 08 December 2025, 16:00-17:00
• Martin Ryle Seminar Room, KICC.

If you have a question about this talk, please contact km723.

Artificial Intelligence/Machine learning (AI/ML), especially deep learning, is becoming increasingly popular. Many also believe they are having/will have transformational impacts on many scientific fields. But important questions remain, such as: - Are these methods really that different from traditional statistical approaches? - How, exactly, do they even work? - Why, in particular, should we even expect them to work? - And, most importantly: what will it take to believe them when they make novel discoveries? I’ll try to lead discussion on some of these questions, highlight some of the practical and philosophical areas they intersect with, and aim to provide some answers/perspectives on some of them (as time permits).

This talk is part of the Astro Data Science Discussion Group series.

This talk is included in these lists:

• Astro Data Science Discussion Group
• Cambridge Astronomy Talks
• Combined External Astrophysics Talks DAMTP
• Cosmology, Astrophysics and General Relativity
• Institute of Astronomy Extra Talks
• Institute of Astronomy Talk Lists
• Martin Ryle Seminar Room, KICC

Note that ex-directory lists are not shown.