Integrate-and-Fire Neurons for Low-Powered Pattern Recognition

TL;DR

This paper presents a low-power Integrate-and-Fire neuron model for pattern recognition in embedded systems, demonstrating its effectiveness through simulation and hardware implementation with promising energy efficiency.

Contribution

It introduces a novel, trainable Integrate-and-Fire neuron model using RC circuits, suitable for low-power neuromorphic hardware in pattern recognition tasks.

Findings

Hardware implementation shows promising energy efficiency.

Model successfully trained on dog posture dataset.

Recurrent form enables complex pattern recognition.

Abstract

Embedded systems acquire information about the real world from sensors and process it to make decisions and/or for transmission. In some situations, the relationship between the data and the decision is complex and/or the amount of data to transmit is large (e.g. in biologgers). Artificial Neural Networks (ANNs) can efficiently detect patterns in the input data which makes them suitable for decision making or compression of information for data transmission. However, ANNs require a substantial amount of energy which reduces the lifetime of battery-powered devices. Therefore, the use of Spiking Neural Networks can improve such systems by providing a way to efficiently process sensory data without being too energy-consuming. In this work, we introduce a low-powered neuron model called Integrate-and-Fire which exploits the charge and discharge properties of the capacitor. Using parallel and series RC circuits, we developed a trainable neuron model that can be expressed in a recurrent form. Finally, we trained its simulation with an artificially generated dataset of dog postures and implemented it as hardware that showed promising energetic properties. This paper is the full text of the research, presented at the 20th International Conference on Artificial Intelligence and Soft Computing Web System (ICAISC 2021)