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 Uroš 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. All interested members of the UC Berkeley and Berkeley Lab communities are welcome and encouraged to attend. To receive email notifications about upcoming meetings, or to request more information, please contact the organizers (Vanessa Boehm, Marin Bukov, and Ben Nachman) at firstname.lastname@example.org.
All interested members of the UC Berkeley and LBNL communities are welcome and encouraged to attend. To recieve email notifications about meetings, please join the BIDS mailing list here. The traffic on this list is minimal (1-2 emails/week).
Please, sign up for our google group on berkeleymlforum in order to receive updates and announcements!
Our meetings are located in the BIDS space for the semester (190 Doe Library).
- January 27, 2020, 1:30pm: Marin Bukov (Physics, UC Berkeley). Title: Reinforcement Learning to Control Quantum Systems.
- February 10, 2020, 1:30pm: Wahid Bhimji (NERSC): Title: Probabilistic programming and Deep Learning at scale for science.
- February 24, 2020, 1:30pm: Stephan Hoyer (Google). Title: Deep learning for PDEs, and scientific computing with JAX.
- March 9, 2020, 1:30pm: Charles Fisher (Unlearn.AI). Title: BoltGAN Machines and Applications in Medicine.
- March 23, 2020, 1:30pm: Vanessa Boehm (UC Berkeley). Title: Deep Generative Models for Scientific Applications
- April 6, 2020, 1:30pm: Yang Song (Computer Science Department, Stanford). Title: Estimating Gradients of Distributions for Generative Modeling
- April 20, 2020, 1:30pm: Samuel Hopkins (EECS Theory group, UC Berkeley). Title: Robust Mean Estimation in Nearly-Linear Time, with Applications to Outlier Removal.
- May 4, 2020, 1:30pm: Jack Collins (Physics, SLAC). Title: Representation Learning for Particle Collider Events.
- May 11, 2020, 1:30pm: Jason Rocks (Physics, Boston University). Title: Over-fitting in Modern Supervised Learning: Memorization, Interpolation, and Decomposition of Errors.
- June 1, 2020, 1:30pm: Joaquin Rodriguez Nieva (Physics, Stanford). Title: Identifying topological order through unsupervised machine learning
- June 15, 2020, 1:30pm: Michaela Paganini (Facebook AI Research). Title: TBD.
- June 29, 2020, 1:30pm:
- A family of algorithms for interpreting manifold embedding coordinates in molecular dynamics data, Samson Koelle
- Probing Dark Matter with Strong Gravitational Lensing, Simon Birrer
- The role of machine learning in building an earthquake disaster platform, Qingkai Kong
- Anomaly Detection meets Deep Learning
- Uncertainties in Neural Networks: Methods and Applications
- Neural Ordinary Differential Equations
- Machine Learning for Approximating Sub-Grid Physics in Electromagnetic Geophysics (Lindsey Heagy)
- The Recurrent Inference Machine: applications to Astronomical and Medical imaging
- Interpretable machine learning - what does it actually mean? (Jamie Murdoch)
- Learning on unstructured spherical grids (Max Jiang)
- Power of gradients and accept-reject step in MCMC algorithms (Raaz Dwivedi)
- JUNIPR: a framework for unsupervised and interpretable machine learning in particle physics (Anders Andreassen)
- Efficient coding and language evolution: the case of color naming (Noga Zaslavskya)
- Sampling vs Optimization (Yian Ma)
- Deep Learning with symmetries (Tess Smidt)
- Latest development in Recurrent Neural Networks (Ravi Krishna)
- Fundamentals of graph theory and application to population migrations (Wooseok Ha)
- Deep Learning in Bio-imaging (Henry Pinkard)
- Applications of ML for High Energy Physics (Ben Nachman)