We demonstrate a novel edge-contact floating gate transistor (ECFGT) based on phase engineered MoS <inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</inf> for in-memory computing. The ECFGT performs ultra-high operation speed (10ns for programming and 100ns for erasing), low operation voltage (15V) and a significantly reduced power consumption (~11.5 fJ/per program, ~41.3 fJ/per erase). Besides, good endurance (>8×10 4 ) for multi-level conductance is demonstrated, and 5-bit distinguishable states in our device are utilized as synapses for neuromorphic computing. The ultra-small read currents (10 -12 ~10 -6 A) in the subthreshold mode of the individual devices illuminate the promise of constructing very large-scale neural network through device integration.
No takes yet. Share an insight, caveat, or question.
Yu et al. (2024) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: