Automatic Feature Selection via Neuroevolution (2005)
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:

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