The Machine Learning and Science Forum (formerly the Berkeley Statistics and Machine Learning Forum) meets biweekly to discuss current applications across a wide variety of research domains in the physical sciences and beyond. Hosted by UC Berkeley Physics Professor and BIDS Senior Fellow Uros Seljak, these active sessions bring together domain scientists, statisticians, and computer scientists who are either developing state-of-the-art methods or are interested in applying these methods in their research. To receive email notifications about upcoming meetings, or to request more information, please contact berkeleymlforum@gmail.com. All interested members of the UC Berkeley and Berkeley Lab communities are welcome and encouraged to attend.
Spring 2020:
- January 27, 2020: Reinforcement Learning to Control Quantum Systems, Marin Bukov, Physics, UC Berkeley
- February 10, 2020: Probabilistic programming at scale for science, Wahid Bhimji, NERSC
- February 24, 2020: Deep learning for PDEs, and scientific computing with JAX, Stephan Hoyer, Google
- March 9, 2020: BoltGAN Machines and Applications in Medicine, Charles K. Fisher, Unlearn.AI
- March 23, 2020: Deep generative models for scientific applications, Vanessa Böhm, BCCP
- April 6, 2020: Estimating Gradients of Distributions for Generative Modeling, Yang Song, Computer Science, Stanford
- April 20, 2020: Robust Mean Estimation in Nearly-Linear Time, with Applications to Outlier Removal, Sam Hopkins, EECS, UC Berkeley
- May 4, 2020: Representation Learning for Particle Collider Events, Jack Collins, Physics, SLAC
- May 11, 2020: Over-fitting in Modern Supervised Learning: Memorization, Interpolation, and Decomposition of Errors, Jason Rocks, Physics, Boston University
- May 18, 2020: TBD
- May 25, 2020: TBD
Previous Sessions
- December 16, 2019: A family of algorithms for interpreting manifold embedding coordinates in molecular dynamics data (Samson Koelle)
- December 2, 2019: Probing Dark Matter with Strong Gravitational Lensing (Simon Birrer)
- November 18, 2019: The role of machine learning in building an earthquake disaster platform (Qingkai Kong)
- November 4, 2019: Anomaly Detection Meets Deep Learning
- October 21: 2019: Uncertainties with Neural Networks: Methods and Applications
- October 7, 2019: Neural Ordinary Differential Equations
- September 23, 2019: Machine learning for approximating sub-grid physics in electromagnetic geophysics (Lindsey Heagy)
- September 9, 2019: The Recurrent Inference Machine: applications to Astronomical and Medical imaging
- April 15, 2019: Interpretable machine learning - what does it actually mean? (Jamie Murdoch)
- April 1, 2019: Learning on unstructured spherical grids (Max Jiang)
- March 18, 2019: Power of gradients and accept-reject step in MCMC algorithms (Raaz Dwivedi)
- March 4, 2019: JUNIPR: a framework for unsupervised and interpretable machine learning in particle physics (Anders Andreassen)
- February 4, 2019: Efficient coding and language evolution: the case of color naming (Noga Zaslavskya)
- December 10, 2018: Sampling vs Optimization (Yian Ma)
- November 26, 2018: Deep Learning with symmetries (Tess Smidt)
- October 15, 2018: Latest development in Recurrent Neural Networks (Ravi Krishna)
- October 8, 2018: Fundamentals of graph theory and application to population migrations (Wooseok Ha)
- October 1, 2018: Deep Learning in Bio-imaging (Henry Pinkard)
- September 24, 2018: Applications of ML for High Energy Physics (Ben Nachman)
