E411 Innovation Hall
43 Colchester Ave
Burlington, VT 05405
United States
- Ph.D., Computational Biology - Cornell University
- B.S., Applied Mathematics - University of Vermont
BIO
Nick Cheney is an Associate Professor of Computer Science and a core faculty in Complex Systems and Data Science. His research is in bio-inspired artificial intelligence. His research lab, the UVM Neurobotics Lab, draws inspiration from natural systems, and especially biological learning processes (e.g. evolution, development, and lifelong learning) to design machine learning algorithms which create more flexible, scalable, and context-aware robots and decision-making systems (particularly, deep neural networks). This work in automated machine learning (AutoML) aims to automate many of the unintuitive challenges of designing robot and machine learning systems/architectures/pipelines -- helping to reduce the barriers to entry for those new to the field. His lab also works with domain experts across a variety of fields, helping to automate and scale their scientific and clinical pipelines towards this goal.
Prior to joining the faculty at UVM, Nick was a Research Assistant Professor at the University of Wyoming, working alongside Jeff Clune. Nick received his Ph.D. from Cornell University, studying Computational Biology under Hod Lipson and Steve Strogatz, while also serving as a research fellow at NASA Ames, the Santa Fe Institute, and Columbia University. Prior to that, Nick received a B.S. in Applied Mathematics from the University of Vermont.
Courses
- CS 3870 / CSYS 5870 — Data Science I
- CS 6520 / CSYS 6520 — Evolutionary Computation
- CS 6690 / CSYS 6690 —The Surprises of Deep Learning
Publications
Nick Cheney's Publications on Google Scholar
Area(s) of expertise
Machine Learning, Deep Learning, Meta-Learning, AutoML, Evolutionary Computation, Evolutionary Robotics
Bio
Nick Cheney is an Associate Professor of Computer Science and a core faculty in Complex Systems and Data Science. His research is in bio-inspired artificial intelligence. His research lab, the UVM Neurobotics Lab, draws inspiration from natural systems, and especially biological learning processes (e.g. evolution, development, and lifelong learning) to design machine learning algorithms which create more flexible, scalable, and context-aware robots and decision-making systems (particularly, deep neural networks). This work in automated machine learning (AutoML) aims to automate many of the unintuitive challenges of designing robot and machine learning systems/architectures/pipelines -- helping to reduce the barriers to entry for those new to the field. His lab also works with domain experts across a variety of fields, helping to automate and scale their scientific and clinical pipelines towards this goal.
Prior to joining the faculty at UVM, Nick was a Research Assistant Professor at the University of Wyoming, working alongside Jeff Clune. Nick received his Ph.D. from Cornell University, studying Computational Biology under Hod Lipson and Steve Strogatz, while also serving as a research fellow at NASA Ames, the Santa Fe Institute, and Columbia University. Prior to that, Nick received a B.S. in Applied Mathematics from the University of Vermont.
Courses
- CS 3870 / CSYS 5870 — Data Science I
- CS 6520 / CSYS 6520 — Evolutionary Computation
- CS 6690 / CSYS 6690 —The Surprises of Deep Learning
Publications
Areas of Expertise
Machine Learning, Deep Learning, Meta-Learning, AutoML, Evolutionary Computation, Evolutionary Robotics
Websites:
Selected Publications:
Beaulieu, S., Frati, L., Miconi, T., Lehman, J., Stanley, K. O., Clune, J. & Cheney, N. (2020). Learning to Continually Learn. 24th European Conference on Artificial Intelligence.
Cheney, N., Bongard, J., SunSpiral, V., & Lipson, H. (2018). Scalable co-optimization of morphology and control in embodied machines. Journal of The Royal Society Interface, 15(143), 20170937.
Cheney, N., MacCurdy, R., Clune, J., & Lipson, H. (2013). Unshackling evolution: evolving soft robots with multiple materials and a powerful generative encoding. In Proceedings of the Fifeenth Annual Conference on Genetic and Evolutionary Computation (pp. 167-174). ACM.