Neuromorphic Computing with Ferroelectric FinFETs in the Presence of Temperature, Process Variation, Device Aging and Flicker Noise
This work addresses reliability challenges for neuromorphic computing in edge AI devices, though it is incremental as it builds on existing ferroelectric FinFET technology.
This paper investigated how temperature changes, process variation, device aging, and flicker noise affect the inference accuracy of pre-trained all-ferroelectric FinFET deep neural networks, demonstrating minimal impact from variation and noise, with gate bias optimization recovering accuracy from temperature-induced degradation and showing endurance over 10^8 cycles and retention over 10 years.
This paper reports a comprehensive study on the impacts of temperature-change, process variation, flicker noise and device aging on the inference accuracy of pre-trained all-ferroelectric (FE) FinFET deep neural networks. Multiple-level-cell (MLC) operation with a novel adaptive-program-and-read algorithm with 100ns write pulse has been experimentally demonstrated in 5 nm thick hafnium zirconium oxide (HZO)-based FE-FinFET. With pre-trained neural network (NN) with 97.5% inference accuracy on MNIST dataset as baseline, device to device variation is shown to have negligible impact. Flicker noise characterization at various bias conditions depicts that drain current fluctuation is less than 0.7% with virtually no inference accuracy degradation. The conductance drift of a programmed cell, as an aftermath of temperature change, was captured by a compact model over a wide range of gate biases. Despite significant inference accuracy degradation at 233K for a NN trained at 300K, gate bias optimization for recovering the accuracy is demonstrated. Endurance above 10$^8$ cycles and extrapolated retention above 10 years are shown, which paves the way for edge device artificial intelligence with FE-FinFETs.