English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

This paper reports a comprehensive study on the impacts oftemperature-change, process variation, flicker noise and device aging on theinference accuracy of pre-trained all-ferroelectric (FE) FinFET deep neuralnetworks. Multiple-level-cell (MLC) operation with a noveladaptive-program-and-read algorithm with 100ns write pulse has beenexperimentally demonstrated in 5 nm thick hafnium zirconium oxide (HZO)-basedFE-FinFET. With pre-trained neural network (NN) with 97.5% inference accuracyon MNIST dataset as baseline, device to device variation is shown to havenegligible impact. Flicker noise characterization at various bias conditionsdepicts that drain current fluctuation is less than 0.7% with virtually noinference accuracy degradation. The conductance drift of a programmed cell, asan aftermath of temperature change, was captured by a compact model over a widerange of gate biases. Despite significant inference accuracy degradation at233K for a NN trained at 300K, gate bias optimization for recovering theaccuracy is demonstrated. Endurance above 10$^8$ cycles and extrapolatedretention above 10 years are shown, which paves the way for edge deviceartificial intelligence with FE-FinFETs.

Neuromorphic Computing with Ferroelectric FinFETs in the Presence of Temperature, Process Variation, Device Aging and Flicker Noise