2023
DOI: 10.1088/2634-4386/accc51
|View full text |Cite
|
Sign up to set email alerts
|

Parallel synaptic design of ferroelectric tunnel junctions for neuromorphic computing

Abstract: We propose a novel synaptic design of more efficient neuromorphic edge-computing with substantially improved linearity and extremely low variability. Specifically, a parallel arrangement of ferroelectric tunnel junctions with an incremental pulsing scheme provides a great improvement in linearity for synaptic weight updating by averaging weight update rates of multiple devices. To enable such desing with ferroelectric tunnel junction building blocks, we have demonstrated the lowest reported variability: σ/μ = … Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...

Citation Types

0
1
0

Year Published

2023
2023
2025
2025

Publication Types

Select...
4
1

Relationship

1
4

Authors

Journals

citations
Cited by 5 publications
(1 citation statement)
references
References 42 publications
0
1
0
Order By: Relevance
“…Moon et al [3] presented an effective method to address another technical challenge for resistive memory-based neuromorphic circuits, namely, the nonlinear weight updates. By using multiple ferroelectric tunnel junctions in parallel as a single synapse, the variability in the weight update is averaged out, resulting in the lowest reported cycle-to-cycle and device-to-device variabilities across multiple dies in an 8 inch wafer.…”
mentioning
confidence: 99%
“…Moon et al [3] presented an effective method to address another technical challenge for resistive memory-based neuromorphic circuits, namely, the nonlinear weight updates. By using multiple ferroelectric tunnel junctions in parallel as a single synapse, the variability in the weight update is averaged out, resulting in the lowest reported cycle-to-cycle and device-to-device variabilities across multiple dies in an 8 inch wafer.…”
mentioning
confidence: 99%