Jonathan Mugan

Adjunct Professor
jmugan [at] cs [dot] utexas [dot] edu

My research focuses on the goal of making computers intelligent through access to context and knowledge. An intuitive example is that navigation systems help you get to where you want to go by knowing where you are (context) and by knowing the layout of the roads (knowledge).

My PhD thesis focused on the question of how a robot can acquire knowledge through autonomous exploration. As a postdoc at Carnegie Mellon University, I explored how computers can use both context and feedback to learn the privacy preferences of users of mobile devices. My current research focuses on enabling computers to autonomously and adaptively protect themselves against cyber attacks.


Selected Publications: 

Jonathan Mugan and Benjamin Kuipers.
Autonomous Learning of High-Level States and Actions in Continuous Environments
IEEE Transactions on Autonomous Mental Development (TAMD). 2012. 

Justin Cranshaw, Jonathan Mugan and Norman Sadeh.
User-Controllable Learning of Location Privacy Policies with Gaussian Mixture Models
Proceedings of the Twenty-Fifth Conference on Artificial Intelligence (AAAI-11). 2011.

Jonathan Mugan and Benjamin Kuipers.
Autonomously Learning an Action Hierarchy Using a Learned Qualitative State Representation
Proceedings of the 21st International Joint Conference on Artificial Intelligence (IJCAI-09). 2009.

Jonathan Mugan and Klaus Truemper. 
Discretization of Rational Data. 
In Mathematical Methods for Knowledge Discovery and Data Mining.  
IGI Publishing Group. 2008.

Jonathan Mugan and Benjamin Kuipers.
Learning to Predict the Effects of Actions: Synergy Between Rules and Landmarks
Proceedings of the 6th (IEEE) International Conference on Development and Learning (ICDL-07). 2007.

  • "The Curiosity Cycle: Preparing Your Child for the Ongoing Technological Explosion"