The Berkeley Institute for Data Science (BIDS) Machine Learning and Science Forum meets biweekly to discuss current applications across a wide variety of research domains in the physical sciences and beyond. Hosted by BIDS Affiliates Physics Professor Uroš Seljak and LBNL Physics Staff Scientist Ben Nachman, 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, Aditi Krishnapriyan, Vinicius Mikuni, Mariel Pettee, and Shashank Subramania) at firstname.lastname@example.org.
See also the BIDS event listing.
All interested members of the UC Berkeley and LBNL communities are welcome and encouraged to attend. To receive 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! When signing up, please give a short description of who you are and your interests in machine learning!
Our meetings are located in the BIDS space (190 Doe Library), but are currently being held on Zoom until further notice.
- September 13, 2021, 11 am PST: Vinicius Mikuni (LBNL). Title: Point cloud applications to collider physics.
- September 27, 2021, 11 am PST: Mariel Pettee (LBNL). Title: ML Methods for Particle Physics and Choreography.
- October 11, 2021, 11 am PST: Jaideep Pathak (LBNL). Title: TBA.
- October 25, 2021, 11 am PST: Serena Wang (UC Berkeley). Title: TBA.
- November 8, 2021, 11 am PST: Speaker TBD.
- November 22, 2021, 11 am PST: Speaker TBD.
- December 6, 2021, 11 am PST: Speaker TBD.
- December 20, 2021, Holiday break – no speaker.
- January 24, 2022, 11 am PST: Speaker TBD.
- February 7, 2022, 11 am PST: Speaker TBD.
- February 21, 2022, 11 am PST: President’s Day – no speaker.
- March 7, 2022, 11 am PST: Speaker TBD.
- March 21, 2022, 11 am PST: Anima Anandkumar. Title: TBD.
- April 4, 2022, 11 am PST: Timnit Gebru. Title: TBD.
- April 18, 2022, 11 am PST: Speaker TBD.
- May 2, 2022, 11 am PST: Speaker TBD.
- May 16, 2022, 11 am PST: Speaker TBD.
- May 30, 2022, 11 am PST: Speaker TBD.
- September 14, 2020, Time 11 am: Michaela Paganini (Facebook AI Research). Title: Comprehension is compression: understanding neural networks through pruning and the lottery ticket hypothesis.
- September 28, 2020, Time 11 am: Chirag Modi (UC Berkeley). Title: FlowPM: Distributed TensorFlow Implementation of Cosmological N-body Solver.
- October 12, 2020, Time 11 am: Adam Sadilek (Google). Title: Machine-Learned Epidemiology.
- October 26, 2020, Time 11 am: Yasaman Bahri (Google). Title: The Large Learning Rate Phase of Deep Learning.
- November 9, 2020, Time 11 am: Xiangyang Ju (LBNL). Title: First-class machine learning model for Science: Graph Neural Network.
- November 23, 2020, Time 11 am: Nicole Hartman (SLAC). Title: Set and Sequence Machine Learning for Particle Identification at the Large Hadron Collider.
- December 7, 2020, Time 11 am: Ian Convy (UC Berkeley). Title: Mutual Information Estimation for Tensor Network Machine Learning.
- December 21, 2020, Time 11 am: Christmas break. Happy Holidays!
- January 25, 2021, Time 11 am: Debbie Bard (NERSC). Title: AI at the exascale.
- February 8, 2021, Time 11 am: Omri Azencot (Ben-Gurion Univeristy). Title: Latent Vector Recurrent Models.
- February 22, 2021, Time 11 am: Soon Hoe Lim (KTH). Title: Noisy Recurrent Neural Networks
- March 8, 2021, Time 11 am: George Stein (LBL / UC Berkeley). Title: Self-Supervised Representation Learning for Astronomical Images.
- March 22, 2021, Time 11 am: Jascha Sohl-Dickstein (Google). Title: Understanding overparameterized neural networks.
- April 5, 2021, Time 11 am: Christian Herwig (Fermilab). Title: An ML Control System for the Fermilab Booster.
- April 19, 2021, Time 11 am: Akshunna Shaurya Dogra (UC Berkeley). Title: Improving neural network based equations solvers.
- May 3, 2021, Time 11 am: Nikhil Rao (Amazon). Title: HypE: Learning Knowledge Graph Entity Representations in Hyperbolic Space.
- June 14, 2021, Time 11 am: Liam Hodgkinson (UC Berkeley). Title: Training stochastic differential equation models using ordinary differential equations.
- 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
- 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)