Hardware-Based Spiking Neural Networks Using Capacitor-Less Positive Feedback Neuron Devices

• Published in: IEEE transactions on electron devices 2021-09, Vol.68 (9), p.4766-4772
• Main Authors: Kwon, Dongseok, Woo, Sung Yun, Bae, Jong-Ho, Lim, Suhwan, Park, Byung-Gook, Lee, Jong-Ho
• Format: Article
• Language: English
• Subjects: Anodes; Biological neural networks; Capacitors; Electric potential; Hardware; Leaky integrate and fire (LIF) neuron; Membrane potentials; Micromechanical devices; Neural networks; neuromorphic; Neurons; Positive feedback; positive feedback (PF) devices; Signal processing; Spiking; spiking neural networks (SNNs); Training
• ISSN: 0018-9383; 1557-9646
• DOI: 10.1109/TED.2021.3098503

In this article, hardware-based spiking neural networks (SNNs) using capacitor-less positive feedback (PF) neuron devices are designed. It was reported that the PF device can simultaneously process the excitatory and inhibitory signals. The PF device shows very steep subthreshold slope (SS < 1 mV/dec) due to the PF opertaion, leading to low-power and reliable neuron device. The PF devices also show the behavior of leaky integrate and fire (LIF) neuron, which is the most popular neuron model in SNNs. For hardware configuration, the neuron characteristics of PF device are investigated with the transient behavior of the anode current. Based on the PF neuron devices, the SNN shows the accuracy of 98.19% for the Modified National Institute of Standards and Technology (MNIST) database classification in four-hidden layer, fully-connected neural network, which is near the accuracy (98.46%) of the artificial neural networks using rectified linear unit (ReLU) activation function.