• Intended to provide a machine-learning based replacement for the L-BFGS-B gradient descent approach used by DRAGLINE
  • Evaluated the performance of simple feed-forward neural networks when tasked with predicting optimal paths through racecourses.
  • Provided the author an excuse to naively apply newly acquired machine-learning knowledge to a completely inappropriate problem.

Written to fulfill the requirements of the University of Utah Honors Program, my undergraduate honors thesis involved designing, training and evaluating different feed-forward neural networks for use in a proposed ML-powered replacement for the DRAGLINE shortest path system.

Link to Thesis