Thursday, October 22nd, 2020 3:00-4:00 PM
Using Big Data to Learn from Small Data, Nathan Hodas (Pacific Northwest National Laboratory, Data Science and Analytics)
Big science has often been accompanied by big data, but scientists have often been stymied by the best way to leverage their data-rich observations. By combining advanced scientific computing with cutting edge deep learning, we have been able to broadly apply deep learning through-out our scientific mission. From high energy physics to computational chemistry to cyber-security, we are enhancing the pace and impact of diverse scientific disciplines by bringing together domain scientists and deep learning researchers across our laboratory. We are seeing in field after field, deep learning is driving transformational innovation, opening the door to a future of data-driven scientific discovery. However, many labels are extremely expensive to obtain or even impossible to obtain more than one, such as a specific astronomical event or scientific experiment. Combining domain knowledge with data driven methods allows us to drive down required data substantially. In fact, by combining vast amounts of labeled surrogate data with advanced few-shot learning, we have demonstrated success in leveraging only one-to-five examples to produce effective deep learning models. In this talk, we will discuss these exciting results and explore the scientific innovations that made this possible.
Thursday, October 15th, 2020 3:00-4:00 PM
Environmental Geonomics: using big datasets to answer questions about tiny ecosystems in the face of climate change, Professor Robin Kodner, Huxley College of the Environment Western Washington University
Tiny microbes and their complex communities can have large impacts on their environment. Microbes are critical for global carbon and nitrogen cycling, can cause harmful blooms in the environment or can cause large-scale disease. Microbial communities can range from very diverse and dynamic, to relatively simple and stable. My lab at Western Washington has been studying two local ecosystems that fall on opposite ends of this complexity spectrum: Bellingham Bay, a dynamic estuary, and the North Cascades snowy alpine environments. I use a range of techniques from microscopy to data-intensive environmental genomics and bioinformatics to observe the diversity and dynamics of microbial eukaryote communities. This talk will discuss ways in which biologists use large environmental genomic datasets to study these ecosystems in ways that weren’t available a decade ago. I will also share examples for what we have learned from these kinds of large datasets in our local microbial ecosystems from Bellingham Bay and the North Cascade mountains.
Thursday, October 8th, 2020 3:00-4:00 PM
Machine Learning for Science: Data-Driven Discovery Methods for Governing equations, Coordinates and Sensors, Professor Nathan Kutz, Department of Applied Mathematics, UW
Machine learning and artificial intelligence algorithms are now being used to automate the discovery of governing physical equations and coordinate systems from measurement data alone. However, positing a universal physical law from data is challenging: (i) An appropriate coordinate system must also be advocated and (ii) simultaneously proposing an accompanying discrepancy model to account for the inevitable mismatch between theory and measurements must be considered. Using a combination of deep learning and sparse regression, specifically the sparse identification of nonlinear dynamics (SINDy) algorithm, we show how a robust mathematical infrastructure can be formulated for simultaneously learning physics models and their coordinate systems. This can be done with limited data and sensors. We demonstrate the methods on a diverse number of examples, showing how data can maximally be exploited for scientific and engineering applications. The work also highlights the fact that the naive application of ML/AI will generally be insufficient to extract universal physical laws without further modification.
Bio: Nathan Kutz is the Yasuko Endo and Robert Bolles Professor of Applied Mathematics at the University of Washington, having served as chair of the department from 2007-2015. He has a wide range of interests, including neuroscience to fluid dynamics where he integrates machine learning with dynamical systems and control.