Meta-optic accelerators for object classifier

Hanyu Zheng, Quan Liu, You Zhou, Ivan I. Kravchenko, Yuankai Huo, Jason Valentine

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

A meta-optic platform for accelerating object classification is demonstrated. End-to-end design is used to co-optimize the optical and digital systems resulting in a high-speed and robust classifier with 93.1% accuracy in classifying handwritten digits.

Original languageEnglish
Title of host publicationCLEO
Subtitle of host publicationScience and Innovations, CLEO:S and I 2023
PublisherOptical Society of America
ISBN (Electronic)9781957171258
DOIs
StatePublished - 2023
EventCLEO: Science and Innovations, CLEO:S and I 2023 - Part of Conference on Lasers and Electro-Optics 2023 - San Jose, United States
Duration: May 7 2023May 12 2023

Publication series

NameCLEO: Science and Innovations, CLEO:S and I 2023

Conference

ConferenceCLEO: Science and Innovations, CLEO:S and I 2023 - Part of Conference on Lasers and Electro-Optics 2023
Country/TerritoryUnited States
CitySan Jose
Period05/7/2305/12/23

Fingerprint

Dive into the research topics of 'Meta-optic accelerators for object classifier'. Together they form a unique fingerprint.

Cite this