Abstract
A spiking neural network (SNN) is a type of artificial neural network that operates based on discrete spikes to process timing information, similar to the manner in which the human brain processes real-world problems. In this paper, we propose a new spiking neural network (SNN) based on conventional, biologically plausible paradigms, such as the leaky integrate-and-fire model, spike timing-dependent plasticity, and the adaptive spiking threshold, by suggesting new biological models; that is, dynamic inhibition weight change, a synaptic wiring method, and Bayesian inference. The proposed network is designed for image recognition tasks, which are frequently used to evaluate the performance of conventional deep neural networks. To manifest the bio-realistic neural architecture, the learning is unsupervised, and the inhibition weight is dynamically changed; this, in turn, affects the synaptic wiring method based on Hebbian learning and the neuronal population. In the inference phase, Bayesian inference successfully classifies the input digits by counting the spikes from the responding neurons. The experimental results demonstrate that the proposed biological model ensures a performance improvement compared with other biologically plausible SNN models.
Wongyu Lee
Researcher, FOUNT
His research interests include machine learning algorithms, specifically spiking neural network (SNN) and reinforcement learning.
Youjung Seo
Researcher, KLA
Her research interests include biomedical signal processing, e-health and machine learning algorithms.
Choongseop Lee
Researcher, LG PRI
His research interests include machine learning and computational neuroscience.
Woojoon Seok
Researcher, Samsung DS
His research interests include biomedical signal processing and machine learning algorithms.
Cheolsoo Park
Professor
His research interests include machine learning, adaptive signal processing, computational neuroscience, and wearable technology.