Pyramidal Neural Networks with Variable Receptive Fields Designed by Genetic Algorithms
Alessandra M. Soares, Bruno Fernandes, Carmelo J. A. Bastos-Filho · 2015
Pyramidal Neural Networks (PNN) are computational systems inspired in the concept of receptive fields from the human visual system. In the original approach, the size of the receptive field within the same 2D layer is constant. However, their size is variable in the human visual system. This paper proposes a PNN with variable receptive fields, which might be determined by a Genetic Algorithm, called Variable Pyramidal Neural Network with Genetic Algorithms (VPNN-GA). We observed from preliminary experiments aiming at detecting faces in images that our approach can achieve better classification rates than the original.