Cem C Tutum
Former 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.
Generalization of Agent Behavior through Explicit Representation of Context Cem Tutum, Suhaib Abdulquddos, Risto Miikkulainen In Proceedings of the 3rd IEEE Conference on Games( ), 2021. 2021

Adapting to Unseen Environments through Explicit Representation of Context Cem C Tutum, Risto Miikkulainen In Proceedings of the 2020 Conference on Artificial Life (ALIFE 2020), 581--588, Montreal, Ca... 2020

Functional Generative Design of Mechanisms with Recurrent Neural Networks and Novelty Search Cameron R. Wolfe, Cem C. Tutum and Risto Miikkulainen To Appear In Proceedings of the Genetic and Evolutionary Computation Conference (GECCO 2019),... 2019

Functional Generative Design: An Evolutionary Approach to 3D-Printing Cem C. Tutum, Supawit Chockchowwat, Etienne Vouga and Risto Miikkulainen To Appear In Proceedings of Genetic and Evolutionary Computation Conference (GECCO 2018), 8, ... 2018

Evolutionary Decomposition for 3D Printing 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) (Bes... 2017

Efficient Sampling for Design Optimization of an SLS Product Nancy Xu, Cem C. Tutum In Proceedings of the 28th Annual International Solid Freeform Fabrication Symposium, 12, Aus... 2017

Surrogate-based Evolutionary Optimization for Friction Stir Welding Cem C Tutum, Shaayaan Sayed and Risto Miikkulainen In Proceedings of IEEE World Congress on Computational Intelligence (WCCI 2016), 8 pages, Van... 2016

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