Professor Risto Miikkulainen
Risto
Miikkulainen, Ph.D. is Professor of Computer Science and
Neuroscience at the University of Texas at Austin and Director of the
UTCS Neural Networks Research Group.
Risto’s research focuses on biologically-inspired computation such as
neural
networks and genetic algorithms. On the one hand, the goal is to better
understand biological information processing, and on the other, to
develop more intelligent artificial systems that learn and adapt by
observing and interacting with the environment.
His three
main focus
areas are: (1) Cognitive Science, i.e. models of natural language
processing, concept learning, and schema-based vision; (2) Computational
Neuroscience, i.e. episodic memory and development, plasticity, and
function of the visual cortex; and (3) Neuroevolution, i.e. evolving
neural
networks with genetic algorithms for sequential decision tasks such as
robotics, games, and artificial life.
Risto is an author of over 250 articles on neuroevolution, connectionist
natural language processing, and the computational neuroscience of the
visual cortex. He is an editor of Neural
Networks,
IEEE Transactions on Computational Intelligence and AI in Games,
Cognitive Systems Research, and IEEE Transactions on
Autonomous Mental
Development.
He is also on the editorial boards of Evolutionary Intelligence
and Machine Learning.
He authored
Subsymbolic Natural Language Processing: An Integrated Model of
Scripts,
Lexicon, and Memory,
coauthored
Computational Maps in the Visual Cortex, and coedited
Advances in Self-Organizing Maps: 7th International Workshop, WSOM
2009,
St. Augustine, Florida.
Risto’s papers include
Evolving Neural Networks through Augmenting Topologies,
Intrusion Detection with Neural Networks,
Incremental Evolution of Complex General Behavior,
A Taxonomy for Artificial Embryogeny,
Forming neural networks through efficient and adaptive
coevolution,
Competitive coevolution through evolutionary
complexification,
Real-Time Neuroevolution in the NERO Video Game,
Solving Non-Markovian Control Tasks with Neuroevolution,
and
Natural Language Processing With Modular
PDP Networks and Distributed Lexicon.
His patents include
Crash prediction network with visual input for vehicle,
Method and apparatus for providing real-time machine learning to
computer-controlled agents used in video games,
Crash prediction network with graded warning for vehicle,
and
Systems and methods for adaptive medical decision support.
Risto earned his M.S. in Applied Mathematics at the Helsinki University
of Technology, Finland in 1986. He earned his Ph.D. in Computer Science
at
the University of California, Los Angeles (UCLA)
in 1990.
Watch
Risto Miikkulainen: How can a system as complex as the human visual
system be constructed? and
Unreal game bots pass Turing test.