ReSNN-DCT: Methodology for Reduction of the Spiking Neural Network Using Discrete Cosine Transform and Elegant Pairing

In recent years, the use of artificial neural network applications to perform object classification and event prediction has increased, mainly from research about deep learning techniques running on hardware such as GPU and FPGA. The interest in the use of neural networks extends to embedded systems, due to the development of applications in smart mobile devices, such as cell phones, drones, autonomous cars and industrial robots. In this article, a methodology is proposed that allows to reduce a spiking neural network, applying the discrete cosine transform (DCT) and elegant pairing. The Izhikevich model was used as a basis for the architecture of the spiking neural network. The simulation results demonstrate the effectiveness of the methodology, showing the feasibility of reducing synapses, applying the DCT transform, and of reducing neurons from the intermediate layers, using the elegant pairing technique of the coefficients, and maintaining the accuracy of the response of the spiking neural network. The results also demonstrate the contribution of the proposed methodology to the scalability of the neural network, with the increase in the storage capacity of the coefficients of the SNN layers.