Training Finite State Classifiers to Improve PCR Primer Design. Preservation
Submitted to CEC2004

Daniel Ashlock, T.J. Wen, and Andrew Wittrock

Abstract PDF eprint

We present preliminary results on training finite state machines as good/bad classifiers for PCR primers. Novel features of the work presented include hybridization of multiple populations and an incremental fitness function. The system presented here is a post-production add-on to a standard primer picking program intended to compensate for organism and lab specific factors.