neural networks research group
areas
•
people
•
projects
•
demos
•
publications
•
software/data
•
Utilizing Symmetry in Evolutionary Design
Active from 2007 - 2010
Can symmetry be utilized as a design principle to constrain evolutionary search, making it more effective? This dissertation aims to show that this is indeed the case, in two ways. First, an approach called ENSO is developed to evolve modular neural network controllers for simulated multilegged robots. Inspired by how symmetric organisms have evolved in nature, ENSO utilizes group theory to break symmetry systematically, constraining evolution to explore promising regions of the search space. As a result, it evolves effective controllers even when the appropriate symmetry constraints are difficult to design by hand. The controllers perform equally well when transferred from simulation to a physical robot. Second, the same principle is used to evolve minimal-size sorting networks. In this different domain, a different instantiation of the same principle is effective: building the desired symmetry step-by-step. This approach is more scalable than previous methods and finds smaller networks, thereby demonstrating that the principle is general. Thus, evolutionary search that utilizes symmetry constraints is shown to be effective in a range of challenging applications.
People
Vinod Valsalam
Ph.D. Alumni
vkv [at] alumni utexas net
Demos
Evolving Controllers for Physical Multilegged Robots
Vinod Valsalam
2011
Evolving Controller Symmetry for Multilegged Robots
Vinod Valsalam
2010
Modular Neuroevolution for Multilegged Locomotion
Vinod Valsalam
2008
Publications
Using Symmetry and Evolutionary Search to Minimize Sorting Networks
Vinod K. Valsalam and Risto Miikkulainen
Journal of Machine Learning Research
, 14(Feb):303--331, 2013.
2013
Constructing Controllers for Physical Multilegged Robots using the ENSO Neuroevolution Approach
Vinod K. Valsalam, Jonathan Hiller, Robert MacCurdy, Hod Lipson and Risto Miikkulainen
Evolutionary Intelligence
, 5(1):1--12, 2012.
2012
Evolving Symmetry for Modular System Design
Vinod K. Valsalam and Risto Miikkulainen
IEEE Transactions on Evolutionary Computation
, 15(3):368--386, 2011.
2011
Utilizing Symmetry and Evolutionary Search to Minimize Sorting Networks
Vinod K. Valsalam and Risto Miikkulainen
Technical Report AITR-11-09, Department of Computer Sciences, The University of Texas at Austin, Aus...
2011
Utilizing Symmetry in Evolutionary Design
Vinod Valsalam
PhD Thesis, Department of Computer Sciences, The University of Texas at Austin, Austin, TX, 2010. Te...
2010
Evolving Symmetric and Modular Neural Network Controllers for Multilegged Robots
Vinod K. Valsalam and Risto Miikkulainen
In
xploring New Horizons in Evolutionary Design of Robots: Workshop at the 2009 IEEE/RSJ Internat...
2009
Evolving Symmetric and Modular Neural Networks for Distributed Control
Vinod K. Valsalam and Risto Miikkulainen
In
Proceedings of the Genetic and Evolutionary Computation Conference (GECCO)
, 731--738, 200...
2009
Modular Neuroevolution for Multilegged Locomotion
Vinod K. Valsalam and Risto Miikkulainen
In
Proceedings of the Genetic and Evolutionary Computation Conference GECCO 2008
, 265-272, Ne...
2008
Software/Data
ENSO
This package contains software implementing the ENSO approach for evolving symmetric modular neural networks. It also in...
2010
Sorting Networks
This package contains software utilizing an approach based on symmetry and evolution to minimize the number of comparato...
2010
Related Areas
Evolutionary Computation
Neuroevolution
Control
Robotics