| Literature DB >> 27874238 |
Elliot J Fuller1, Farid El Gabaly1, François Léonard1, Sapan Agarwal2, Steven J Plimpton2, Robin B Jacobs-Gedrim2, Conrad D James2, Matthew J Marinella2, A Alec Talin1.
Abstract
Nonvolatile redox transistors (NVRTs) based upon Li-ion battery materials are demonstrated as memory elements for neuromorphic computer architectures with multi-level analog states, "write" linearity, low-voltage switching, and low power dissipation. Simulations of backpropagation using the device properties reach ideal classification accuracy. Physics-based simulations predict energy costs per "write" operation of <10 aJ when scaled to 200 nm × 200 nm.Keywords: data storage; nanodevices; transistors
Year: 2016 PMID: 27874238 DOI: 10.1002/adma.201604310
Source DB: PubMed Journal: Adv Mater ISSN: 0935-9648 Impact factor: 30.849