Jason Zhi Liang
Ph.D. Student
Jason's work focuses on bilevel optimization, i.e. evolving the parameters of an evolutionary optimization algorithm. He has applied this approach to evolution of neural networks in control tasks as well as in optimization benchmark tasks with good results.
Bilevel Optimization of the Helicopter Hovering Control TaskJason Zhi Liang and Risto Miikkulainen2015
Evolutionary Architecture Search For Deep Multitask Networks Jason Liang, Elliot Meyerson, and Risto Miikkulainen In Proceedings of the Genetic and Evolutionary Computation Conference (GECCO), 8, Kyoto, Japa... 2018

Evolutionary Neural Architecture Search for Deep Learning Jason Zhi Liang PhD Thesis, The University of Texas at Austin, 2317 Speedway, Austin, TX 78712, December 2018. 2018

Evolving Deep Neural Networks Risto Miikkulainen, Jason Liang, Elliot Meyerson, Aditya Rawal, Dan Fink, Olivier Francon, Bala Raju... In Robert Kozma, Cesare Alippi, Yoonsuck Choe, and Francesco Carlo Morabito, editors, Artificial ... 2018

{UT} {A}ustin {V}illa: {R}obo{C}up 2015 3{D} Simulation League Competition and Technical Challenges Champions Patrick MacAlpine and Josiah Hanna and Jason Liang and Peter Stone In Luis Almeida and Jianmin Ji and Gerald Steinbauer and Sean Luke, editors, {R}obo{C}up-2015: Ro... 2016

Evolutionary Bilevel Optimization for Complex Control Problems and Blackbox Function Optimization Jason Zhi Liang Masters Thesis, Department of Computer Sciences, The University of Texas at Austin, Austin, Texas, 2... 2015

Evolutionary Bilevel Optimization for Complex Control Tasks Jason Zhi Liang, Risto Miikkulainen In Proceedings of the Genetic and Evolutionary Computation Conference (GECCO 2015), 8, Madrid... 2015