One-vs-One, One-vs-Rest, and a novel Outcome-Driven One-vs-One binary classifiers enabled by optoelectronic memristors towards overcoming hardware limitations in multiclass classification

Deep neural networks have achieved considerable success over the past ten years in a variety of fields. However, current state-of-the-art artificial intelligence (AI) systems require large computing hardware infrastructure and high power consumption. To overcome these hurdles, it is required to adop...

Full description

Bibliographic Details

Published in:	Discover materials Vol. 4; no. 1; pp. 7 - 13
Main Authors:	Psaltakis, George, Rogdakis, Konstantinos, Loizos, Michalis, Kymakis, Emmanuel
Format:	Journal Article
Language:	English
Published:	Cham Springer International Publishing 03-03-2024 Springer Nature B.V Springer
Subjects:	Accuracy Algorithms Biomaterials Characterization and Evaluation of Materials Chemistry and Materials Science Classification Energy consumption Energy Materials Internet of Things Light Materials Science Metallic Materials Neural networks Pattern recognition Structural Materials
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!