BIDMaP is happy to be jointly hosting this year's seminar series with colleagues in computational physical sciences, including collaborators from the departments of Physics and Astronomy, and the Lawrence Berkeley National Laboratory.
In silico materials design often involves the exploration of vast, diverse chemical spaces. While ab initio methods have been phenomenally successful in materials simulations, their scope of application has always been constrained by their high cost and poor scaling. In this talk, I will highlight...
The success of deep learning has hinged on learned functions dramatically outperforming hand-designed functions for many tasks. However, we still train models using hand designed optimizers acting on hand designed loss functions. I will argue that these hand designed components are typically mismatched to the...
Please join for this EECS Colloquium (not part of the regular BIDMaP series; please note different day/time/location). Many thanks to EECS for welcoming the BIDMaP community to this exciting talk. See more on the EECS website, including a remote participation option.
I will describe a research program aimed at advancing the potential for discovery and interdisciplinary collaboration by approaching fundamental physics challenges through the lens of modern machine learning (ML). This research program has two complementary components. Ab initio simulations are a powerful tool of fundamental...
A central goal of computational chemistry is to predict material properties using first-principles methods based on the fundamental laws of quantum mechanics. However, the high computational costs of these methods typically prevent rigorous predictions of macroscopic quantities at finite temperatures. In this talk, I will...
Alessandra Lanzara is a prominent physicist who has contributed significantly to the field of materials science. After obtaining her PhD from Universita’ di Roma La Sapienza in 1999, she joined the faculty of the physics department at UC Berkeley as an assistant professor. She has...
Fernando Pérez's research focuses on creating tools for modern computational research and data science across domain disciplines, with an emphasis on high-level languages, interactive and literate computing, and reproducible research. Through tools like IPython and Project Jupyter, he builds foundational blocks that enable scientists to tackle all stages of computational research (from exploration through publication) with a coherent approach, thus improving scientific productivity, collaboration and reproducibility.
Molecular dynamics (MD) simulations offer valuable insights into the atomistic-level behavior of molecular systems. However, large-scale Molecular Dynamics simulations face some limitations. First, the high-dimensional nature of large simulation trajectories can make them difficult to interpret. Second, the accessible sampled timescale is often shorter than...
Recently, artificial intelligence (AI) for drug discovery has raised increasing interest in both the machine learning (ML) and computational chemistry/biology communities. The core task of AI for drug discovery is molecule representation learning, where the molecule knowledge can be naturally presented in different modalities: chemical...
Kristin Persson is a professor in the Department of Materials Science and Engineering at UC Berkeley and runs a lab at the Lawrence Berkeley National Laboratory. The Persson group studies the physics and chemistry of materials using atomistic computational methods and high-performance computing technology, particularly...
Syrine Belakaria is a PhD candidate in Computer Science at Washington State University advised by Prof. Jana Doppa. Prior to her PhD, she received a Master's degree in Electrical Engineering from the University of Idaho where she was advised by Professor Sameh Sorour and received...
Throughout the history of machine learning, we have seen more and more automation of tasks, such as using neural networks to replace the tedious process of manual feature design. One of the next major steps is to automatically design and tune neural networks themselves: neural...
