The Berkeley Statistics and Machine Learning Forum meets biweekly to discuss current applications across a wide variety of research domains and software methodologies. 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. Practical questions about the meetings can be directed to BIDS Data Science Fellow François Lanusse.
All interested members of the UC Berkeley and LBL communities are welcome and encouraged to attend.
Our meetings are located in the BIDS space for the semester (190 Doe Library).
- Oct. 7th, 1:30pm, Neural Ordinary Differential Equations, Amir Gholami
- 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)