CompSci Colloquium: Jeff Clune on "Creating Autonomous Systems"

Creating Autonomous Systems with Deep Learning, Deep Reinforcement Learning, and Bayesian Optimization                
ABSTRACT: I will describe three projects into creating autonomous systems with machine learning. I will first summarize our Nature paper on learning algorithms that enable robots, after being damaged or encountering novel environmental conditions, to adapt in 1-2 minutes and continue on with their mission. This work combines a novel stochastic optimization algorithm with Bayesian optimization to produce state-of-the-art robot damage recovery. Second, I will describe our work into using deep neural networks to automatically identify, count, and describe the behavior of wild animals in images taken remotely by motion-sensor cameras. These autonomous systems will revolutionize wildlife biology and our ability to understand and protect natural ecosystems. Similar technology could dramatically reduce costs in a number of key industrial sectors, such as monitoring crops or industrial plants. Finally, I will summarize our recent Go-Explore algorithm, which dramatically improves the ability of deep reinforcement learning algorithms to solve previously unsolvable problems wherein reward signals are sparse, meaning that intelligent exploration is required. Go-Explore solves Montezuma’s Revenge, considered by many to be a grand challenge of AI research. I will also very briefly summarize a few other research projects into autonomous systems, including improving their interpretability and enabling them to continuously learn.            
                                
BIO: Jeff Clune is the Loy and Edith Harris Associate Professor in Computer Science at the University of Wyoming and a Senior Research Manager and founding member of Uber AI Labs, which was formed after Uber acquired a startup he helped lead. Jeff focuses on robotics and training deep neural networks via deep learning, including deep reinforcement learning. Since 2015, a robotics paper he co-authored was on the cover of Nature, a deep learning paper from his lab was on the cover of the Proceedings of the National Academy of Sciences, he won an NSF CAREER award, he was an invited speaker at the NeurIPS Deep Reinforcement Learning Workshop, he was invited to give a forthcoming ICML tutorial, and his deep learning papers were awarded honors (best paper awards and/or oral presentations) at the top machine learning conferences (NeurIPS, CVPR, ICLR, and ICML). His research is regularly covered in the press, including the New York Times, NPR, NBC, Wired, the BBC, the Economist, National Geographic, the Atlantic, the New Scientist, the Daily Telegraph, Science, Nature, and U.S. News & World Report. Prior to becoming a professor, he was a Research Scientist at Cornell University, received degrees from Michigan State University (PhD, master’s) and the University of Michigan (bachelor’s).    

Tuesday, March 5, 2019 at 3:30pm to 4:30pm

Discovery Learning Center, DLC 170
1095 Regent Drive, Boulder, CO 80309

Event Type

Colloquium/Seminar

College, School & Unit

Engineering & Applied Science

Group
Computer Science
Add to Calendar
GoogleiCalOutlook

Recent Activity