DC Field | Value | Language |
---|---|---|
dc.contributor.author | Lee, ChangHyeon | ko |
dc.contributor.author | Rahimifard Leila | ko |
dc.contributor.author | Choi Junhwan | ko |
dc.contributor.author | Park Jeong-ik | ko |
dc.contributor.author | LEE, CHUNGRYEOL | ko |
dc.contributor.author | Kumar Divake | ko |
dc.contributor.author | Shukla Priyesh | ko |
dc.contributor.author | LEE, SEUNGMIN | ko |
dc.contributor.author | Trivedi Amit Ranjan | ko |
dc.contributor.author | Yoo Hocheon | ko |
dc.contributor.author | Im Sung Gap | ko |
dc.date.accessioned | 2024-07-25T13:00:09Z | - |
dc.date.available | 2024-07-25T13:00:09Z | - |
dc.date.created | 2024-07-25 | - |
dc.date.issued | 2024-03 | - |
dc.identifier.citation | NATURE COMMUNICATIONS, v.15, no.1 | - |
dc.identifier.uri | http://hdl.handle.net/10203/320371 | - |
dc.description.abstract | Probabilistic inference in data-driven models is promising for predicting outputs and associated confidence levels, alleviating risks arising from overconfidence. However, implementing complex computations with minimal devices still remains challenging. Here, utilizing a heterojunction of p- and n-type semiconductors coupled with separate floating-gate configuration, a Gaussian-like memory transistor is proposed, where a programmable Gaussian-like current-voltage response is achieved within a single device. A separate floating-gate structure allows for exquisite control of the Gaussian-like current output to a significant extent through simple programming, with an over 10000 s retention performance and mechanical flexibility. This enables physical evaluation of complex distribution functions with the simplified circuit design and higher parallelism. Successful implementation for localization and obstacle avoidance tasks is demonstrated using Gaussian-like curves produced from Gaussian-like memory transistor. With its ultralow-power consumption, simplified design, and programmable Gaussian-like outputs, our 3-terminal Gaussian-like memory transistor holds potential as a hardware platform for probabilistic inference computing.,Probabilistic inference hardware prevents overconfidence. Lee et al. report a Gaussian-like memory transistor using p-n junction coupled with separate floating gate, offering precise control of the Gaussian outputs, simplified circuit design, and low power consumption for inference computing., | - |
dc.language | English | - |
dc.publisher | NATURE PORTFOLIO | - |
dc.title | Highly parallel and ultra-low-power probabilistic reasoning with programmable gaussian-like memory transistors | - |
dc.type | Article | - |
dc.identifier.wosid | 001187425700036 | - |
dc.type.rims | ART | - |
dc.citation.volume | 15 | - |
dc.citation.issue | 1 | - |
dc.citation.publicationname | NATURE COMMUNICATIONS | - |
dc.contributor.localauthor | Im Sung Gap | - |
dc.contributor.nonIdAuthor | Rahimifard Leila | - |
dc.contributor.nonIdAuthor | Choi Junhwan | - |
dc.contributor.nonIdAuthor | Park Jeong-ik | - |
dc.contributor.nonIdAuthor | Kumar Divake | - |
dc.contributor.nonIdAuthor | Shukla Priyesh | - |
dc.contributor.nonIdAuthor | Trivedi Amit Ranjan | - |
dc.contributor.nonIdAuthor | Yoo Hocheon | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.