Energy-efficient Hybrid CMOS-NEMS LIF Neuron Circuit in 28 nm CMOS Process

TL;DR

This paper introduces a hybrid CMOS-NEMS neuron circuit for neuromorphic computing in 28 nm technology, achieving significant energy efficiency improvements over traditional CMOS designs.

Contribution

It presents a novel hybrid CMOS-NEMS neuron circuit that reduces leakage power and enhances energy efficiency in deep sub-micron neuromorphic systems.

Findings

35% energy efficiency improvement over CMOS-only circuits

NEM switches further improve scalability and power consumption

Operates with biologically plausible firing rates

Abstract

Designing analog sub-threshold neuromorphic circuits in deep sub-micron technologies e.g. 28 nm can be a daunting task due to the problem of excessive leakage current. We propose novel energy-efficient hybrid CMOS-nano electro-mechanical switches (NEMS) Leaky Integrate and Fire (LIF) neuron and synapse circuits and investigate the impact of NEM switches on the leakage power and overall energy consumption. We analyze the performance of biologically-inspired neuron circuit in terms of leakage power consumption and present new energy-efficient neural circuits that operate with biologically plausible firing rates. Our results show the proposed CMOS-NEMS neuron circuit is, on average, 35% more energy-efficient than its CMOS counterpart with same complexity in 28 nm process. Moreover, we discuss how NEM switches can be utilized to further improve the scalability of mixed-signal neuromorphic circuits.