Fefet-based binarized neural networks under temperature-dependent bit errors

M Yayla, S Buschjäger, A Gupta… - IEEE Transactions …, 2021 - ieeexplore.ieee.org
Ferroelectric FET (FeFET) is a highly promising emerging non-volatile memory (NVM)
technology, especially for binarized neural network (BNN) inference on the low-power edge …

Experimental demonstration of a robust training method for strongly defective neuromorphic hardware

WA Borders, A Madhavan, MW Daniels… - arxiv preprint arxiv …, 2023 - arxiv.org
The increasing scale of neural networks needed to support more complex applications has
led to an increasing requirement for area-and energy-efficient hardware. One route to …

Measurement-driven neural-network training for integrated magnetic tunnel junction arrays

WA Borders, A Madhavan, MW Daniels, V Georgiou… - Physical Review …, 2024 - APS
The increasing scale of neural networks needed to support more complex applications has
led to an increasing requirement for area-and energy-efficient hardware. One route to …

[PDF][PDF] Ensemble learning with discrete classifiers on small devices

S Buschjäger - 2022 - eldorado.tu-dortmund.de
Abstract Machine learning has become an integral part of everyday life ranging from
applications in AI-powered search queries to (partial) autonomous driving. Many of the …