A hierarchical visual recognition model with precise-spike-driven synaptic plasticity

Abstract

Several conventional methods have been implemented in pattern recognition, but few of them have biological plausibility. This paper mimics the hierarchical visual system and uses the precise-spike-driven (PSD) synaptic plasticity rule to learn. The well-known HMAX model imitates the visual cortex and uses Gabor filter and max pooling to extract features. Compared with the traditional HMAX model, our modified model combines with the characteristics of sparse coding, and retains the features of the image in each orientation. In learning layer, it is an effective preparation for the PSD rule that temporal coding conveys precise spatio-temporal information. The PSD rule is simple and efficient in synaptic adaptation, and calculates directly. The results show our scheme provides a powerful approach for handwritten digit recognition in noisy conditions.