C
Charles W. Anderson
Researcher at Colorado State University
Publications - 136
Citations - 8865
Charles W. Anderson is an academic researcher from Colorado State University. The author has contributed to research in topics: Artificial neural network & Reinforcement learning. The author has an hindex of 35, co-authored 129 publications receiving 8182 citations. Previous affiliations of Charles W. Anderson include University of Manitoba & University of Massachusetts Amherst.
Papers
More filters
Proceedings ArticleDOI
Genetic reinforcement learning for neural networks
TL;DR: It is pointed out that the genetic algorithms which have been shown to yield good performance for neural network weight optimization are really genetic hill-climbers, with a strong reliance on mutation rather than hyperplane sampling.
Journal ArticleDOI
Workshops of the Fifth International Brain-Computer Interface Meeting: Defining the Future
Jane E. Huggins,Christoph Guger,Brendan Z. Allison,Charles W. Anderson,Aaron P. Batista,Anne-Marie A-M Brouwer,Clemens Brunner,Ricardo Chavarriaga,Melanie Fried-Oken,Aysegul Gunduz,Disha Gupta,Andrea Kübler,Robert Leeb,Fabien Lotte,Lee E. Miller,Gernot Müller-Putz,Tomasz M. Rutkowski,Michael Tangermann,David E. Thompson +18 more
TL;DR: The Fifth International Brain-Computer Interface Meeting met June 3-7th, 2013 at the Asilomar Conference Grounds, Pacific Grove, California and included 19 workshops covering topics in brain-computer interface and brain-machine interface research.
Journal ArticleDOI
An Experimental System for Advanced Heating, Ventilating and Air Conditioning (HVAC) Control
M. Anderson,Michael R. Buehner,Peter M. Young,Douglas C. Hittle,Charles W. Anderson,Jilin Tu,David A. Hodgson +6 more
TL;DR: In this article, a simple HVAC system, intended for controlling the temperature and flow rate of the discharge air, was built using standard components, and a single integrated environment is created that is used for data acquisition, controller design, simulation, and closed loop controller implementation and testing.
Proceedings Article
Q-Learning with Hidden-Unit Restarting
TL;DR: Platt's resource-allocation network (RAN) is modified for a reinforcement-learning paradigm and to "restart" existing hidden units rather than adding new units.
Proceedings ArticleDOI
To Fear or Not to Fear That is the Question: Code Characteristics of a Vulnerable Functionwith an Existing Exploit
TL;DR: The results show that the difference between a vulnerability that has no exploit and the one that has an exploit can potentially be characterized using the chosen software metrics, and further research is needed using metrics that consider security domain knowledge for enhancing the predictability of vulnerability exploits.