Gavin W. Taylor
United States Naval Academy
Curriculum Vitae
Contact
United States Naval Academy
Department of Computer Science
572M Holloway Rd. Stop 9F
Annapolis, MD 21402-5002
Phone: (410) 293-6816
taylor@usna.edu
http://www.usna.edu/Users/cs/taylor/
Education
Ph.D., Computer Science
Duke University, 2011
M.S., Computer Science
Duke University, 2009
B.S., Mathematics
Davidson College, 2006
Employment
8/2011–
Assistant Professor, Department of Computer Science
United States Naval Academy
Publications
Highly Refereed Conference Papers
Bharat Singh, Soham De, Yangmuzi Zhang, Thomas Goldstein, and Gavin Taylor.
Layer-Specific Adaptive Learning Rates for Deep Networks. In Proceedings of the 14th
IEEE International Conference on Machine Learning and Applications, December 2015.
Gavin Taylor, Kawika Barabin, and Kent Sayre. An Application of Reinforcement
Learning to Supervised Autonomy. In Proceedings of the 20th International Command
and Control Research and Technology Symposium, Annapolis, MD, June 2015.
Gavin Taylor, Connor Geer, and David Piekut. An Analysis of State-Relevance Weights
and Sampling Distributions on L1-Regularized Approximate Linear Programming
Approximation Accuracy. In Proceedings of the 31st International Conference on Machine
Learning, Beijing, China, June 2014.
Gavin Taylor and Ronald Parr. Value Function Approximation in Noisy Environments
Using Locally Smoothed Regularized Approximate Linear Programs. In Conference on
Uncertainty in Artificial Intelligence, pages 835–842, Catalina Island, California, 2012.
1
Marek Petrik, Gavin Taylor, Ronald Parr, and Shlomo Zilberstein. Feature Selection Using Regularization in Approximate Linear Programs for Markov Decision Processes. In Proceedings of the 27th International Conference on Machine Learning, Haifa,
Israel, 2010.
Gavin Taylor and Ronald Parr. Kernelized Value Function Approximation for Reinforcement Learning. In Proceedings of the 26th International Conference on Machine Learning, pages 1017–1024, Montreal, Canada, 2009.
Ronald Parr, Lihong Li, Gavin Taylor, Christopher Painter-Wakefield, and Michael
Littman. An Analysis of Linear Models, Linear Value-Function Approximation, and
Feature Selection for Reinforcement Learning. In International Conference of Machine
Learning, pages 752–759, Helsinki, Finland, 2008.
Technical Reports
Tom Goldstein, Gavin Taylor, Kawika Barabin, and Kent Sayre. Unwrapping ADMM:
Efficient Distributed Computing via Transpose Reduction. Technical report, arXiv,
http://arxiv.org/abs/1504.02147, April 2015.
Gavin Taylor, Connor Geer, and David Piekut. An Analysis of State-Relevance Weights
and Sampling Distributions on L1 -Regularized Approximate Linear Programming
Approximation Accuracy. Technical report, arXiv, http://arxiv.org/abs/1404.4258,
April 2014.
Marek Petrik, Gavin Taylor, Ronald Parr, and Shlomo Zilberstein. Feature Selection Using Regularization in Approximate Linear Programs for Markov Decision Processes. Technical report, arXiv, http://arxiv.org/abs/1005.1860, May 2010.
Book Chapters
Gavin Taylor, Ranjeev Mittu, Ciara Sibley, and Joseph Coyne. Towards modeling the
behavior of autonomous systems and humans for trusted operations. In The Intersection of Robust Intelligence and Trust in Autonomous Systems, chapter 2. Springer, 2015.
Abstracts and Workshops
Gavin Taylor, Kawika Barabin, and Kent Sayre. An Application of Reinforcement
Learning to Supervised Autonomy. In AAAI Symposium on Foundations of Autonomy
and its Threats: From Individuals to Interdependence, Palo Alto, CA, March 2015.
Weiqing Gu, Ranjeev Mittu, Julie Marble, Gavin Taylor, Ciara Sibley, Joseph Coyne,
and William F. Lawless. Toward Modeling the Behavior of Autonomous Systems and
Humans for Trusted Operations. In AAAI Symposium on the Intersection of Robust Intelligence and Trust in Autonomous Systems, 2014.
Julian Mason and Gavin Taylor. An Intensive Introductory Robotics Course Without
Prerequisites. In AAAI Robotics Exhibition and Workshop, July 2010.
Ronald Parr, Gavin Taylor, Christopher Painter-Wakefield, Lihong Li, and Michael
Littman. Linear Value Function Approximation and Linear Models. In Multidisciplinary Symposium on Reinforcement Learning, June 2009. (abstract).
Ali Nouri, Michael Littman, Lihong Li, Ronald Parr, Christopher Painter-Wakefield,
and Gavin Taylor. A Novel Benchmark Methodology and Data Repository for Real2
Life Reinforcement Learning. In Multidisciplinary Symposium on Reinforcement Learning,
June 2009. (abstract).
A. Campbell, L. J. Heyer, M. L. S. Ledbetter, L. L. M. Hoopes, T. T. Eckdahl, A. G.
Rosenwald, E. R. Fowlks, N. Dovidio, M. R. Gordon, D. Moskowitz, M. L. Cowell,
J. Abele, B. Akin, G. Taylor, D. Choi, P. Karnik, P. Lowry, J. M. Madden, E. E. Oldham,
B. Pierce, A. Amore, S. Bossie, M. Citrin, E. Cobain, M. McDonald, M. Solé, E. Wilson, M. g, K. DeCelle, L. Buckwold, B. Whigham, C. A. Zanta, K. Gabric, B. Kittinger,
L. Adler, A. Ryan, and W. T. Hatfield. Microarrays for the Masses: Pedagogical Resources for High School through College. In American Society of Cell Biology, December
2007. (abstract).
Grants
Carl Albing, Nate Chambers, and Gavin Taylor. A Multi-Faceted Approach to Engaging Students with HPC. Department of Defense High Performance Computing
Modernization Program. $450,000/1 year, 2016.
Thomas Goldstein and Gavin Taylor. Highly Distributed Algorithms for Deep Neural Networks. Department of Defense High Performance Computing Modernization
Program. Individual, unfettered access to new 50,000-core Cray XC40, 2015.
Carl Albing, Nate Chambers, and Gavin Taylor. A Multi-Faceted Approach to Engaging Students with HPC. Department of Defense High Performance Computing
Modernization Program. $450,000/1 year, 2015.
Thomas Goldstein and Gavin Taylor. Distributed, Efficient Algorithms for Deep Network Training Without Pretraining. $450,000/3 years. Office of Naval Research, 2015.
Gavin Taylor. Abnormal State Detection Using Value Function Approximation for Unmanned Aerial Vehicles and Multiple Semi-Supervised Classifiers for Cybersecurity.
$87,000/3 years (only accepted first two years). Office of Naval Research, 2013.
Gavin Taylor. L1 Regularization for Value Function Approximation. Naval Academy
Research Committee, 2012.
Magazine Articles
Gavin Taylor and William F. Lawless. Foundations of Autonomy and its (Cyber)
Threats: From Individuals to Interdependence. AI Magazine, 36(3), 2015.
Ranjeev Mittu, Harold Hawkins, Glenn White, William F. Lawless, and Gavin Taylor.
Enhancing a Lightweight FIST2FAC System. Naval Science and Technology Future Force,
December 2014.
Teaching
Fall 2015
SY301: Data Structures for Cybersecurity (2 sections, course coordinator)
SI592: Trident Scholar Project, “Fast, Distributed Algorithms for Deep
Networks,” with MIDN Ryan Burmeister.
Capstone customer and technical advisor
Spring 2015
SI110: Introduction to Cybersecurity (2 sections)
SI496C: Machine Learning (1 section, course coordinator)
3
Fall 2014
SY301: Data Structures for Cybersecurity (2 sections, course coordinator, course creator)
SI495A: Research Course with MIDN Kawika Barabin and MIDN Kent
Sayre
Capstone technical advisor, “SCOUT: A Testbed for Human Control of
Multiple Unmanned Aerial Vehicles”
Spring 2014
SI475: Intelligent Robotics (2 sections, course coordinator)
SI496C: Machine Learning (1 section, course coordinator)
Fall 2013
IC312: Data Structures (3 sections, course coordinator)
SI495A: Research Course with MIDN Connor Geer and MIDN David
Piekut
Capstone customer and technical advisor, “Improved NPC Interactions
in Video Games Via Artificial Intelligence”
Spring 2013
SI475: Intelligent Robotics (1 section, course coordinator)
IC211: Object-Oriented Programming (1 section, course coordinator for
pre-semester curriculum planning, but not once the semester began)
SI486A: Machine Learning (1 section, course coordinator, course creator)
Fall 2012
IC312: Data Structures (3 sections, course coordinator)
SI495A: Research Course with MIDN Matthew Yates
Spring 2012
IC211: Object-Oriented Programming (2 sections, course coordinator)
Fall 2011
IC210: Introduction to Computer Science (2 sections)
Fall 2010
Co-Instructor, Teaching With Robotics (CPS 089S and CPS 196S)
Dr. Jeffrey Forbes
Duke University
Summer 2009
Instructor, Robotics
Duke Talent Identification Program.
Summer 2008
Instructor, Robotics
Duke Talent Identification Program.
Fall 2007
Teaching Assistant, Program Design and Analysis II (CPS 100)
Dr. Jeffrey Forbes
Duke University
Spring 2007
Teaching Assistant, Program Design and Analysis II (CPS 100 and CPS
100E)
Dr. Dietolf Ramm
Duke University
Departmental and Yard-wide Service
8/2015–
Truman Scholarship Committee
8/2015–
Recruitment Committee Chair
8/2015–
Faculty Search Committee
4
8/2014–5/2015
Cyber Operations Faculty Search Committee
8/2014–
Department Honor Liaison
7/2014–5/2015
Plebe Advising
8/2013–5/2014
Cybersecurity Curriculum Committee
1/2013–
Robotics Computer Lab Administrator
8/2012–
Curriculum Committee
8/2011–
Upsilon Pi Epsilon Civilian Representative
8/2011–
Recruitment Committee
8/2011–
Nimitz Librarian Liaison
Academic Community Service
8/2015
Reviewer for Machine Learning
3/2015
Organizer, “AAAI Symposium on Foundations of Autonomy and its
Threats: From Individuals to Interdependence.” AAAI Spring Symposia.
4/2015
Reviewer for IEEE Transactions on Neural Networks and Learning Systems
2/2014
Reviewer for IEEE Transactions on Neural Networks and Learning Systems
10/2013
Reviewer for Journal of Machine Learning Research
5/2013
Proposal Review Panelist, National Science Foundation, Division of
Computer and Network Systems
5/2013
Reviewer for the IEEE Transactions on Neural Networks and Learning
Systems
4/2013
Reviewer for the International Conference on Machine Learning
11/2012
Proposal Review Panelist, National Science Foundation, Division of Information and Intelligent Systems
11/2012
Reviewer for the International Conference on Machine Learning
11/2012
Reviewer for the IEEE Transactions on Neural Networks and Learning
Systems
7/2012
Reviewer for the IEEE Transactions on Neural Networks and Learning
Systems
12/2011
Reviewer for Journal of Artificial Intelligence Research
8/2010–12/2010
Reviewer for AISTATS
8/2010
Reviewer for Machine Learning
4/2010
Reviewer for Machine Learning
5
2/2010
Reviewer for the Journal of Machine Learning Research
6