UTCS Artificial Intelligence
courses
talks/events
demos
people
projects
publications
software/data
labs
areas
admin
Automatic Feature Selection via Neuroevolution (2005)
Shimon Whiteson
,
Peter Stone
,
Kenneth O. Stanley
,
Risto Miikkulainen
, and
Nate Kohl
Feature selection is the process of finding the set of inputs to a machine learning algorithm that will yield the best performance. Developing a way to solve this problem automatically would make current machine learning methods much more useful. Previous efforts to automate feature selection rely on expensive meta-learning or are applicable only when labeled training data is available. This paper presents a novel method called FS-NEAT which extends the NEAT neuroevolution method to automatically determine an appropriate set of inputs for the networks it evolves. By learning the network's inputs, topology, and weights simultaneously, FS-NEAT addresses the feature selection problem without relying on meta-learning or labeled data. Initial experiments in an autonomous car racing simulation demonstrate that FS-NEAT can learn better and faster than regular NEAT. In addition, the networks it evolves are smaller and require fewer inputs. Furthermore, FS-NEAT's performance remains robust even as the feature selection task it faces is made increasingly difficult.
View:
PDF
,
PS
,
HTML
Citation:
In
Proceedings of the Genetic and Evolutionary Computation Conference
, June 2005.
Bibtex:
@InProceedings{GECCO05-fsneat, title={Automatic Feature Selection via Neuroevolution}, author={Shimon Whiteson and Peter Stone and Kenneth O. Stanley and Risto Miikkulainen and Nate Kohl}, booktitle={Proceedings of the Genetic and Evolutionary Computation Conference}, month={June}, url="http://www.cs.utexas.edu/users/ai-lab?whiteson:gecco05", year={2005} }
People
Nate Kohl
Ph.D. Alumni
nate [at] natekohl net
Risto Miikkulainen
Faculty
risto [at] cs utexas edu
Kenneth Stanley
Postdoctoral Alumni
kstanley [at] cs ucf edu
Peter Stone
Faculty
pstone [at] cs utexas edu
Shimon Whiteson
Formerly affiliated Collaborator
s a whiteson [at] uva nl
Areas of Interest
Neuroevolution
Labs
Neural Networks
Learning Agents