NNRG Areas - Machine Learning

Machine Learning

Machine Learning is a very broad category that encompasses most of the work done in the AI Lab in one way or another. Essentially, any system that performs some sort of behavior (defined by a model or policy), and changes its behavior based on data (learns), can be considered a Machine Learning system.

Publications

AutoInit: Analytic Signal-Preserving Weight Initialization for Neural Networks	Garrett Bingham and Risto Miikkulainen	In Proceedings of the 37th AAAI Conference on Artificial Intelligence, 2023. (also arXiv:20...	2023

Optimizing Neural Networks through Activation Function Discovery and Automatic Weight Initialization	Garrett Bingham	PhD Thesis, Department of Computer Science, The University of Texas at Austin, May 2023.	2023

The Traveling Observer Model: Multi-task Learning Through Spatial Variable Embeddings	Elliot Meyerson and Risto Miikkulainen	arxiv:2010.02354, October 2020.	2020

Pseudo-task Augmentation: From Deep Multitask Learning to Intratask Sharing---and Back	Elliot Meyerson, Risto Miikkulainen	In Proceedings of the 35th International Conference on Machine Learning, 739-748, 2018.	2018

Infinite-Word Topic Models for Digital Media	Austin Waters	PhD Thesis, Department of Computer Science, The University of Texas at Austin, 2014.	2014

Online Kernel Selection for Bayesian Reinforcement Learning	Joseph Reisinger and Peter Stone and Risto Miikkulainen	In Proceedings of the Twenty-Fifth International Conference on Machine Learning, July 2008.	2008

Demos

A Neuroevolution Approach to General Atari Game Playing

Matthew Hausknecht

2013