Spiking pattern recognition using informative signal of image and unsupervised biologically plausible learning

Abstract

The recent progress of low-power neuromorphic hardware provides exceptional conditions for applications where their focus is more on saving power. However, the design of spiking neural networks (SNN) to recognize real-world patterns on such hardware remains a major challenge ahead of the researchers. In this paper, SNN inspired by the model of local cortical population as a biological neuro-computing resource for digit recognition was presented. SNN was equipped with spike-based unsupervised weight optimization based on the dynamical behavior of the excitatory (AMPA) and inhibitory (GABA) synapses using Spike Timing Dependent Plasticity (STDP). This biologically plausible learning enables neurons to make decisions and learns the structure of the input examples. There are two main reasons why this structure is state of the art compared to previous works: learning process is compatible with many experimental observations on induction of long-term potentiation and long-term depression, image to signal mapping created an informative signal of the image based on sequences of prolate spheroidal wave functions (PSWFs). The proposed image mapping translates the pixels attributes to the frequency, phase, and amplitude of a sinusoidal signal. This mapping enables the SNN to generalize better to the realistic sized images and significantly decreases the size of the input layer. Cortical SNN compared to earlier related studies recognized MNIST digits more accurate and achieved 96.1% classification accuracy with unsupervised learning based on sparse spike activity.