Particule Swarm Model Selection (PSMS)
H. Jair Escalante, Manuel Montes, L. Enrique Sucar,
Nat. Inst. of Astrophysics Optics and Electronics , Mexico
Neural networks have been proven to be effective learning algorithms since
their introduction. These methods have been widely used in many domains,
including scientific, medical, and commercial applications with great success.
However, selecting the optimal combination of preprocessing methods and hyperparameters
for a given learning algorithm is still a challenge. Recently a novel algorithm
for supervised learning model selection has been proposed: Particle Swarm
Model Selection (PSMS). This algorithm has been proved to be a reliable method
for the selection of optimal learning algorithms together with preprocessing
methods, as well as for hyperparameter optimization. On this paper we applied
PSMS for the selection of the best combination of preprocessing methods and
hyperparameters for a fixed neural network on benchmark data sets from a
challenging competition: the (IJCNN 2007) agnostic vs prior knowledge challenge.
A fair competition which goal is to provide objective comparisons among models
that use prior knowledge of the domain and those that not. In this paper
we further show that the use of PSMS is useful for model selection when we
have no knowledge about the domain we are dealing with. With PSMS we obtained
competitive models that are ranked at the top of the official results ranking.