A Low-Energy High-Density Capacitor-Less I&amp;F Neuron Circuit Using Feedback FET Co-Integrated With CMOS

Min-Woo Kwon,Junil Lee,Kyungchul Park,Byung-Gook Park,Myung-Hyun Baek

doi:10.1109/jeds.2019.2941917

A Low-Energy High-Density Capacitor-Less I&F Neuron Circuit Using Feedback FET Co-Integrated With CMOS

Min-Woo Kwon, Junil Lee + Show 3 more

Open Access

https://doi.org/10.1109/jeds.2019.2941917

Copy DOI

Abstract

We have developed a capacitor-less I&F neuron circuit with a dual gate positive feedback fieldeffect transistor (FBFET) and successfully co-integrated FBFET and CMOS in a wafer. By implementing the neuron circuit with FBFET, we can overcome the limits of conventional CMOS, reduce energy consumption, and imitate the biological neuron. The floating body of the FBFET can replace the membrane capacitor that occupies a large area and performs leaky integration of the neuron. Due to the extremely low sub-threshold swing of the FBFET (less than 0.528mv/dc), energy consumption of the neuron is significantly reduced by suppressing sub-threshold current. Finally, we analyzed the fabricated neuron circuit operation, retention time of the integrated charges and energy consumption compare to conventional CMOS neuron circuit.

Highlights

Various types of the artificial neural model such as I&F neuron, H-H neuron, log domain neuron and tau-cell neuron have been presented [1]–[7]
If the electron concentration exceed the threshold for feedback, the feedback FET (FBFET) is turned on by the positive feedback between the electrons and potential barrier
The smaller the amplitude of the pulse, the fewer electrons are accumulated in the floating body, so a larger number of pulses are required to turn on the FBFET (Fig. 3 (b))

Summary

Introduction

Various types of the artificial neural model such as I&F neuron, H-H neuron, log domain neuron and tau-cell neuron have been presented [1]–[7]. INDEX TERMS Integrate-and-fire neuron circuit, positive feedback FET, low energy consumption, floating body effect. Conventional CMOS based neuron circuits for these biological functions require a large membrane capacitor (Cmem) for integration as well as a number of transistors that result in large cell size and high energy consumption.

Results

Conclusion