A Matching Pursuit Approach for Image Classification with Spiking Neural Networks

The human can learn to recognize objects in a very short time, with few data samples and little computing resources, while achieving high accuracy, that state-of-the-art learning methods hardly approach. In order to emulate the way how the human brain operates in processing external environmental information, a more biologically plausible network, i.e. spiking neural network (SNN), is proposed. In the SNN model, information is encoded into a spatiotemporal spike pattern first, and then SNN learning rules are used to emulate how the human brain works. Therefore, a suitable and appropriate coding method is demanded in SNN. In this paper, we propose a new approach for image recognition tasks, namely MP-SNN, by combining SNN with matching pursuit (NIP). We use the MP encoding method to extract the feature spike pattern from input data, then the tempotron learning algorithm is used to emulate how the brain operates in learning new things and making decisions. The MNIST and its variants are used to evaluate the performance of MP-SNN. Compared with other methods, NIP can generate a more sparse and robust spatiotemporal spike pattern while achieving good learning results. To the best of our knowledge. this paper is the first work to combine NIP and SNN, and gives a more biologically plausible and effective approach in image classification.