Automatic Feature Selection using FS−NEAT
Aksel Ethembabaoglu and Shimon Whiteson
This article describes a series of experiments used to analyze the FS-NEAT method on a double pole-balancing domain. The FS-NEAT method is compared with regular NEAT to discern its strengths and weaknesses. Both FS-NEAT and regular NEAT find a policy, implemented in a neural network, to solve the pole-balancing task by use of genetic algorithms. FS-NEAT, contrary to regular NEAT, uses a different starting population. Whereas regular NEAT networks start out with links between all the inputs and the output, FS-NEAT networks have only one link between an input and the output. It is believed that this more simple starting topology allows for effective feature (input)-selection.