UTCS Artificial Intelligence
I am interested in computational models of cognitive tasks such as language learning, motor learning, and concept formation. I do a lot of sparse / efficient coding to try to uncover possible relationships between sensory and motor codes for cognitive domains. I'm also interested in how these codes interact with unsupervised or minimally supervised techniques for learning control policies.
leif [at] cs utexas edu
Evaluating team behaviors constructed with human-guided machine learning
Igor V. Karpov, Leif M. Johnson and Risto Miikkulainen, To Appear In
Proceedings of the IEEE Conference on Computational Intelligence in Games
, August 31-July 2 2015.
Evaluation Methods for Active Human-Guided Neuroevolution in Games
Igor Karpov, Leif Johnson, Vinod Valsalam and Risto Miikkulainen, In
2012 AAAI Fall Symposium on Robots Learning Interactively from Human Teachers (RLIHT)
, November 2012.
Multiagent Learning through Neuroevolution
Risto Miikkulainen, Eliana Feasley, Leif Johnson, Igor Karpov, Padmini Rajagopalan, Aditya Rawal, and Wesley Tansey, In
Advances in Computational Intelligence
, J. Liu et al. (Eds.), Vol. LNCS 7311, pp. 24-46, Berlin, Heidelberg: 2012. Springer.
The role of uncertainty and reward on eye movements in a virtual driving task
Brian Sullivan, Leif Johnson, Constantin Rothkopf, Mary Hayhoe and Dana Ballard,
Journal of Vision
, Vol. 12, 9 (2012).
A modular reinforcement learning model for human visuomotor behavior in a driving task
Brian Sullivan, Leif Johnson, Dana Ballard and Mary Hayhoe,
Proceedings of the AISB 2011 Symposium on Architectures for Active Vision.
(2011), pp. 33-40.
Areas of Interest
Formerly affiliated with
Embodied Cognition Lab