%0 Journal Article
%T A Spiking Neural Network Based Cortex-Like Mechanism and Application to Facial Expression Recognition
%A Si-Yao Fu
%A Guo-Sheng Yang
%A Xin-Kai Kuai
%J Computational Intelligence and Neuroscience
%D 2012
%I Hindawi Publishing Corporation
%R 10.1155/2012/946589
%X In this paper, we present a quantitative, highly structured cortex-simulated model, which can be simply described as feedforward, hierarchical simulation of ventral stream of visual cortex using biologically plausible, computationally convenient spiking neural network system. The motivation comes directly from recent pioneering works on detailed functional decomposition analysis of the feedforward pathway of the ventral stream of visual cortex and developments on artificial spiking neural networks (SNNs). By combining the logical structure of the cortical hierarchy and computing power of the spiking neuron model, a practical framework has been presented. As a proof of principle, we demonstrate our system on several facial expression recognition tasks. The proposed cortical-like feedforward hierarchy framework has the merit of capability of dealing with complicated pattern recognition problems, suggesting that, by combining the cognitive models with modern neurocomputational approaches, the neurosystematic approach to the study of cortex-like mechanism has the potential to extend our knowledge of brain mechanisms underlying the cognitive analysis and to advance theoretical models of how we recognize face or, more specifically, perceive other people¡¯s facial expression in a rich, dynamic, and complex environment, providing a new starting point for improved models of visual cortex-like mechanism. 1. Introduction Understanding how rapid exposure to visual stimuli (face, objects) affects categorical decision by cortical neuron networks is essential for understanding the relationship between implicit neural information encoding and explicit behavior analysis. Quantitative psychophysical and physiological experimental evidences support the theory that the visual information processing in cortex can be modeled as a hierarchy of increasingly sophisticated, sparsely coded representations, along the visual pathway [1], and that the encoding using pulses, as a basic means of information transfer, is optimal in terms of information transmission. Such a spiking hierarchy should have the unique ability of decorrelating the incoming visual signals, removing the redundant information, while preserving invariability, in an effort to maximize the information gain [2]. Therefore, characterizing and modeling the functions along the hierarchy, from early or intermediate stages such as lateral geniculate nucleus (LGN), or prime visual cortex (V1), are necessary steps for systematic studies for higher level, more comprehensive tasks such as object recognition. However, the
%U http://www.hindawi.com/journals/cin/2012/946589/