Jason Zhi Liang
Ph.D. Alumni
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.
Population-Based Training for Loss Function Optimization 2020
Jason Liang, Santiago Gonzalez, Risto Miikkulainen, To Appear In arXiv:2002.04225 (2020).
Evolutionary Neural AutoML for Deep Learning 2019
Jason Liang, Elliot Meyerson, Babak Hodjat, Dan Fink, Karl Mutch, and Risto Miikkulainen, In Proceedings of the Genetic and Evolutionary Computation Conference (GECCO-2019) 2019.
Evolutionary Architecture Search For Deep Multitask Networks 2018
Jason Liang, Elliot Meyerson, and Risto Miikkulainen, In Proceedings of the Genetic and Evolutionary Computation Conference (GECCO), pp. 8, Kyoto, Japan, July 2018.
Evolutionary Neural Architecture Search for Deep Learning 2018
Jason Zhi Liang, PhD Thesis, The University of Texas at Austin.
Evolving Deep Neural Networks 2018
Risto Miikkulainen, Jason Liang, Elliot Meyerson, Aditya Rawal, Dan Fink, Olivier Francon, Bala Raju, Hormoz Shahrzad, Arshak Navruzyan, Nigel Duffy, and Babak Hodjat, In Artificial Intelligence in the Age of Neural Networks and Brain Computing, Robert Kozma, Cesare Alippi, Yoonsuck Choe, and Francesco Carlo Morabito (Eds.) 2018. Amsterdam: Elsevier.
UT Austin Villa: RoboCup 2015 3D Simulation League Competition and Technical Challenges Champions 2016
Patrick MacAlpine, Josiah Hanna, Jason Liang, and Peter Stone, In {R}obo{C}up-2015: Robot Soccer World Cup {XIX}, Luis Almeida and Jianmin Ji and Gerald Steinbauer and Sean Luke (Eds.), Berlin, Germany 2016. Springer Verlag.
Evolutionary Bilevel Optimization for Complex Control Problems and Blackbox Function Optimization 2015
Jason Zhi Liang, Masters Thesis, Department of Computer Sciences, The University of Texas at Austin.
Evolutionary Bilevel Optimization for Complex Control Tasks 2015
Jason Zhi Liang, Risto Miikkulainen, In Proceedings of the Genetic and Evolutionary Computation Conference (GECCO 2015), pp. 8, Madrid, Spain, July 2015.
Bilevel Optimization of the Helicopter Hovering Control TaskJason Zhi Liang and Risto Miikkulainen2015
Formerly affiliated with Neural Networks