DISC (Discussion in Scientific Computing) is a biweekly seminar offering students and researchers a relaxed setting to share their research, explore new ideas, and learn about the work being done across the mathematical and scientific computing community at Emory.
During Fall 2026 (and maybe also Spring 2027), we will explore Mathematical Approaches to Machine Learning: the intersection of computational mathematics and machine learning, from mathematical foundations and hybrid methods to critical discussions of current approaches. Whether you're looking to share your work or simply learn something new, DISC is a welcoming space for everyone.
BOOKS:
Deep Learning - Goodfellow, Bengio & Courville (MIT Press, 2016)
Data-Driven Science and Engineering - Brunton & Kutz (Cambridge, 2nd ed. 2022)
Inverse Problems and Data Assimilation - Sanz-Alonso, Stuart & Taeb (Cambridge, 2023)
Deep Learning: Foundations and Concepts - C.M. Bishop & H. Bishop (Springer, 2023)
PAPERS:
Physics-Informed Neural Networks - Raissi, Perdikaris & Karniadakis (J. Comput. Phys., 2019)
ML for Inverse Problems and Data Assimilation - Bach, Baptista, Sanz-Alonso & Stuart (arXiv:2410.10523, 2024)
Solving Inverse Problems in Medical Imaging with Score-Based Generative Models - Song, Shen, Xing & Ermon (ICLR 2022)
Fourier Neural Operator for Parametric PDEs - Li et al. (ICLR 2021)
DeepONet: Learning Nonlinear Operators - Lu, Jin, Pang, Zhang & Karniadakis (Nature Machine Intelligence, 2021)
Score-Based Generative Modeling through SDEs - Song, Sohl-Dickstein, Kingma, Kumar, Ermon & Poole (ICLR 2021)
Stochastic Interpolants: A Unifying Framework for Flows and Diffusions - Albergo & Vanden-Eijnden (arXiv:2209.15571, 2023)
Discovering Governing Equations from Data via SINDy - Brunton, Proctor & Kutz (PNAS, 2016)
Mathematical Introduction to Deep Learning: Methods, Implementations, and Theory - Jentzen, Kuckuck & von Wurstemberger (arXiv:2310.20360, 2023)
Attention Is All You Need - Vaswani et al. (NeurIPS 2017)
Highly Accurate Protein Structure Prediction with AlphaFold - Jumper et al. (Nature, 2021)
Neural Scaling Laws - Kaplan, McCandlish, Henighan et al. (arXiv:2001.08361, 2020)