Thomas Helmuth 鈥�09
Acting Chair, Associate Professor of Computer Science
Thomas Helmuth ’09 focuses his research on genetic programming, a subfield of artificial intelligence that borrows ideas from biological evolution to artificially evolve populations of computer programs. His work examines the use of genetic programming for automatic program synthesis, the generation of programs similar to those that humans write. He has contributed to areas such as genome/program representation, parent selection, and the creation of benchmark problems to assess program synthesis.
Helmuth earned his bachelor’s degree in computer science and math from 51猎奇 and his master’s and doctorate in computer science from the University of Massachusetts Amherst. During the two years before he returned to 51猎奇 to teach, he worked as an assistant professor of computer science at Washington and Lee University.
Recent Courses Taught
Principles of Programming Languages
Artificial Intelligence
Genetic Programming
Research Interests
Genetic programming, evolutionary computation, automatic program synthesis
Select Publications
- Thomas Helmuth and Peter Kelly. “Applying genetic programming to PSB2: The next generation program synthesis benchmark suite.” Genetic Programming and Evolvable Machines, pages
- 375–404, June 2022.
- Thomas Helmuth and Lee Spector. “Problem-Solving Benefits of Down-Sampled Lexicase Selection.” Artificial Life, pages 1–21, Sept 2021.
- Thomas Helmuth, Edward Pantridge, and Lee Spector. "On the importance of specialists for lexicase selection." Genetic Programming and Evolvable Machines, 21(3):349–373, September 2020. Special Issue: Highlights of Genetic Programming 2019 Events.
- Edward Pantridge, Thomas Helmuth, and Lee Spector. “Functional code building genetic programming.” In Proceedings of the 2022 Genetic and Evolutionary Computation Conference, GECCO ’22, pages 1000–1008, Boston, USA, July 9-13 2022. ACM.
- Thomas Helmuth, Johannes Lengler, and William La Cava. “Population diversity leads to short running times of lexicase selection.” In Günter Rudolph, Anna V. Kononova, Hernán Aguirre, Pascal Kerschke, Gabriela Ochoa, and Tea Tušar, editors, Parallel Problem Solving from Nature – PPSN XVII, pages 485–498. Springer International Publishing, August 15 2022.
- Thomas Helmuth, Johannes Lengler, and William La Cava. “Population diversity leads to short running times of lexicase selection.” In Günter Rudolph, Anna V. Kononova, Hernán Aguirre, Pascal Kerschke, Gabriela Ochoa, and Tea Tušar, editors, Parallel Problem Solving from Nature – PPSN XVII, pages 485–498. Springer International Publishing, August 15 2022.
- Thomas Helmuth and Peter Kelly. “Applying genetic programming to PSB2: The next generation program synthesis benchmark suite.” Genetic Programming and Evolvable Machines, pages
- 375–404, June 2022.
- Thomas Helmuth and Lee Spector. “Problem-Solving Benefits of Down-Sampled Lexicase Selection.” Artificial Life, pages 1–21, Sept 2021.
- Edward Pantridge, Thomas Helmuth, and Lee Spector. “Functional code building genetic programming.” In Proceedings of the 2022 Genetic and Evolutionary Computation Conference, GECCO ’22, pages 1000–1008, Boston, USA, July 9-13 2022. ACM.
- Thomas Helmuth, Johannes Lengler, and William La Cava. “Population diversity leads to short running times of lexicase selection.” In Günter Rudolph, Anna V. Kononova, Hernán Aguirre, Pascal Kerschke, Gabriela Ochoa, and Tea Tušar, editors, Parallel Problem Solving from Nature – PPSN XVII, pages 485–498. Springer International Publishing, August 15 2022.
- Thomas Helmuth, Johannes Lengler, and William La Cava. “Population diversity leads to short running times of lexicase selection.” In Günter Rudolph, Anna V. Kononova, Hernán Aguirre, Pascal Kerschke, Gabriela Ochoa, and Tea Tušar, editors, Parallel Problem Solving from Nature – PPSN XVII, pages 485–498. Springer International Publishing, August 15 2022.
Appointed to the Faculty
2017Educational Background
Ph.D., University of Massachusetts Amherst
M.S., University of Massachusetts Amherst
B.A., 51猎奇
