Abstract: Machine learning researchers have developed many flavors of generative models. In all cases, these models have particular characteristics that make them more or less suited for certain problems. For example, Restricted Boltzmann Machines (RBMs) are well-suited to modeling both discrete and continuous variables and enable one to sample from any conditional distribution of the model, but it's difficult to train them to learn complex distributions. By contrast, Generative Adversarial Networks (GANs) can be trained to learn complex distributions, but are not well-suited to modeling discrete variables and do not allow for sampling from arbitrary conditional distributions. Combining the two approaches to create a new type of generative model -- a BoltGAN Machine -- enables one to learn complex discrete or continuous distributions and to sample from arbitrary conditional distributions. These qualities are necessary for using machine learning to address many problems in medical research, so the methodological developments will be motivated by these applications. Full details about this meeting will be posted here: https://bids.github.io/MLStatsForum/.
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 email@example.com. All interested members of the UC Berkeley and Berkeley Lab communities are welcome and encouraged to attend.
Charles K. Fisher
Charles K. Fisher, PhD, is a scientist with interests at the intersection of physics, machine learning, and computational biology. Previously, he worked as a machine learning engineer at Leap Motion and a computational biologist at Pfizer. He was a Philippe Meyer Fellow in theoretical physics at École Normale Supérieure in Paris, France, and a postdoctoral scientist in biophysics at Boston University. Charles holds a PhD in biophysics from Harvard University and a BS in biophysics from the University of Michigan.