Cem C Tutum
Formerly affiliated Research Scientist
I am a Research Scientist at UT-Austin (Department of Computer Science) and NNAISENSE (Intelligent Automation group).

I have been working on a DARPA-funded project as part of the Lifelong Learning Machines (L2M) program since June'18: STELLAR (Super Turing Evolving Lifelong Learning ARchitecture).

I am a mechanical engineer by training (B.Sc. in System Dynamics and Control, M.Sc. in Solid Mechanics and Ph.D. in Manufacturing Engineering), but optimization and its applications in various disciplines have always been in the center of my research interests:
  • Evolutionary computation for
    • single, multi and many-objective & constrained optimization problems,
    • training neural networks (neuroevolution) for reinforcement learning problems,
  • Surrogate-based efficient blackbox optimization for compute-heavy problems,
  • Additive manufacturing processes,
  • Functional Generative Design for 3D printed parts or mechanisms,
  • Multi-physics computer simulations of manufacturing processes.
Homepage:
https://www.cs.utexas.edu/people/faculty-researchers/cem-tutum
Publications
Generalization of Agent Behavior through Explicit Representation of Context 2021
Cem Tutum, Suhaib Abdulquddos, Risto Miikkulainen, In Proceedings of the 3rd IEEE Conference on Games, , 2021.
Adapting to Unseen Environments through Explicit Representation of Context 2020
Cem C Tutum, Risto Miikkulainen, In Proceedings of the 2020 Conference on Artificial Life (ALIFE 2020), pp. 581--588, Montreal, Canada, July 2020. The MIT Press.
Functional Generative Design of Mechanisms with Recurrent Neural Networks and Novelty Search 2019
Cameron R. Wolfe, Cem C. Tutum and Risto Miikkulainen, To Appear In Proceedings of the Genetic and Evolutionary Computation Conference (GECCO 2019), pp. 7, Prague, Czech Republic, July 2019.
Functional Generative Design: An Evolutionary Approach to 3D-Printing 2018
Cem C. Tutum, Supawit Chockchowwat, Etienne Vouga and Risto Miikkulainen, To Appear In Proceedings of Genetic and Evolutionary Computation Conference (GECCO 2018), pp. 8, Kyoto, Japan, July 2018.
Efficient Sampling for Design Optimization of an SLS Product 2017
Nancy Xu, Cem C. Tutum, In Proceedings of the 28th Annual International Solid Freeform Fabrication Symposium, pp. 12, Austin, TX, August 2017.
Evolutionary Decomposition for 3D Printing 2017
Eric A. Yu, Jin Yeom, Cem C. Tutum, Etienne Vouga, Risto Miikkulainen, To Appear In Proceedings of The Genetic and Evolutionary Computation Conference (GECCO 2017) (Best Paper Award), pp. 8 pages, Berlin, Germany, July 2017.
Surrogate-based Evolutionary Optimization for Friction Stir Welding 2016
Cem C Tutum, Shaayaan Sayed and Risto Miikkulainen, In Proceedings of IEEE World Congress on Computational Intelligence (WCCI 2016), pp. 8 pages, Vancouver, BC, Canada, July 2016.
Areas of Interest
Applications Evolutionary Computation Game Playing Multiobjective Optimization Neuroevolution Reinforcement Learning
Software/Data
ContextSkillCARLA Code relating to the experiments involved in studying the effectiveness of the Context+Skill neural network applied to t... 2022
ContextSkillFlappyBall Download at GitHub.

Context-skill model for extrapolati...

2021
Labs
Formerly affiliated with Neural Networks