Brad Fullmer
Undergraduate Alumni
Brad was the first person in NNRG to work on evolution of neural networks, or neuroevolution, back in 1991. He developed a method inspired by DNA structure of start and end markers and introns, and completed an honors thesis on applying it to behavior of artificial agents.
Evolving Finite State Behavior using Marker-Based Genetic Encoding of Neural Networks Brad Fullmer Technical Report HR-91-01, Department of Computer Science, The University of Texas at Austin, 1991. 1991

Using Marker-Based Genetic Encoding Of Neural Networks To Evolve Finite-State Behaviour Brad Fullmer and Risto Miikkulainen In Francisco J. Varela and Paul Bourgine, editors, Toward a Practice of Autonomous Systems: {P}ro... 1991