Hierarchical K-Means Algorithm for Modeling Visual Area V2 Neurons

Abstract. Computational studies about the properties of the receptive fields of neurons in the cortical visual pathway of mammals are abundant in the literature but most addressed neurons in the primary visual area (V1). Recently, the sparse deep belief network (DBN) was proposed to model the response properties of neurons in the V2 area. By investigating the factors that contribute to the success of the model, we find that a simple algorithm for data clustering, K-means algorithm can be stacked into a hierarchy to reproduce these properties of V2 neurons, too. In addition, it is computationally much more efficient than the sparse DBN