Alan's work with NNRG focused on
1. Evolutionary Annealing -- a martingale-based approach to optimization.
2. Neuroannealing -- using evolutionary annealing to learn neural networks.
3. Formal analysis of Iterative Stochastic Optimizers -- a measure theoretic approach to analyzing optimizer performance.
After graduating, he moved to a postdoc position with Prof. Juergen Schmidhuber at IDSIA in Lugano, Switzerland beginning. His position is funded by an NSF grant under the International Research Fellows Program, and the topic is "Deep Neural Networks for the Integration of Perception and Action in Robotic Controllers."
alan lockett [at] gmail com