Hybrid Stochastic Synapses Enabled by Scaled Ferroelectric Field-effect Transistors

TL;DR

This paper demonstrates a novel three-state ferroelectric FET device that enables hybrid stochastic synapses, combining long-term and short-term memory, with potential for energy-efficient neuromorphic computing and improved learning capabilities.

Contribution

It introduces a scalable 28nm FeFET-based three-state stochastic synapse, combining experimental validation with a probabilistic model, advancing multi-state device applications in neuromorphic systems.

Findings

Successful experimental measurement of a 28nm FeFET device.

Development of a probabilistic model for hybrid stochastic synapses.

Hardware-algorithm analysis shows improved on-chip learning with 2-tier memory.

Abstract

Achieving brain-like density and performance in neuromorphic computers necessitates scaling down the size of nanodevices emulating neuro-synaptic functionalities. However, scaling nanodevices results in reduction of programming resolution and emergence of stochastic non-idealities. While prior work has mainly focused on binary transitions, in this work we leverage the stochastic switching of a three-state ferroelectric field effect transistor (FeFET) to implement a long-term and short-term 2-tier stochastic synaptic memory with a single device. Experimental measurements are performed on a scaled 28nm high-$k$ metal gate technology-based device to develop a probabilistic model of the hybrid stochastic synapse. In addition to the advantage of ultra-low programming energies afforded by scaling, our hardware-algorithm co-design analysis reveals the efficacy of the 2-tier memory in comparison to binary stochastic synapses in on-chip learning tasks -- paving the way for algorithms exploiting multi-state devices with probabilistic transitions beyond deterministic ones.