Developing IoT Applications Using Spiking Neural Networks Framework

Abstract

With the recent progress in SNN(Spiking Neural Networks), IoT applications require more intelligent data processing that can operate on neuromorphic hardware. However, as there is no development environment where SNN frameworks can be applied to existing IoT applications, it is difficult for IoT developers to utilize neuromorphic hardware. In this paper, we present a new development framework of IoT applications using SNN as a machine learning solution, called NA-Designer. It has GUI based neural network editor to quickly generate SNN components that can be run on various neuromorphic hardware. In particular, this component is designed to interwork with other IoT framework such as Node-RED. We implement NA-Designer and core neural networks libraries and measure its performance. Our framework can be used to develop Edge computing applications that utilize neuromorphic hardware to reduce energy consumption and latency.