optimization

Beyond Gradients

Alan J. Lockett's Research Pages
English

Neuroannealing

Neuroannealing is the application of evolutionary annealing to the space of neural networks. Neural networks encode a function from inputs to outputs and can be used to solve control problems. In order to apply evolutionary annealing to neural networks, neuroannealing uses a specialized partitioning method to generate the partition tree. The principles of neuroevolution are applied in the variation phase in order to generate new networks. Neuroannealing effectively learns controllers for complex but moderately-sized tasks. The details can be found in Chapter 13 of my thesis.

About Me

Alan J. Lockett

I am looking for an assistant professorship to research the theory of feedback controllers for the control of complex autonomous systems, from smart homes to self-driving cars and humanoid robots. A CV and research statement can be found in the links to the left.

I have published on the theory of global optimization, humanoid robotics, neural networks for perception and control, and opponent modelling in games, and am working on a book expanding my Ph.D. thesis about the theory of global optimization under contract with Springer.

I am currently a postdoctoral fellow at the Dalle Molle Institute for Artificial Intelligence Studies on a US National Science Foundation postdoc grant working with Juergen Schmidhuber in Lugano, Switzerland. My Ph.D. is from the University of Texas where I studied with Risto Miikkulainen. See my About page for contact information and more.