3 papers
eess.IV2019
Algorithmic Design and Implementation of Unobtrusive Multistatic Serial LiDAR Image
Chi Ding, Zheng Cao, Matthew S. Emigh +6
To fully understand interactions between marine hydrokinetic (MHK) equipment and marine animals, a fast and effective monitoring system is required to capture relevant information…
cs.AI2018
Guided Policy Exploration for Markov Decision Processes using an Uncertainty-Based Value-of-Information Criterion
Isaac J. Sledge, Matthew S. Emigh, Jose C. Principe
Reinforcement learning in environments with many action-state pairs is challenging. At issue is the number of episodes needed to thoroughly search the policy space. Most convention…
cs.LG2016
Information Theoretic-Learning Auto-Encoder
Eder Santana, Matthew Emigh, Jose C Principe
We propose Information Theoretic-Learning (ITL) divergence measures for variational regularization of neural networks. We also explore ITL-regularized autoencoders as an alternativ…