Researchers Submit Patent Application, "Reconfigurable, Hyperdimensional Neural Network Architecture", for Approval (USPTO 20240185591).
In: Blood Weekly, 2024-06-27, S. 840-840
serialPeriodical
Zugriff:
A patent application has been submitted for a reconfigurable, hyperdimensional neural network architecture. Traditional deep neural network architectures are power-intensive and not suitable for low-power devices. The proposed architecture aims to be memory and energy efficient, with a feature extractor neural network that encodes input information into hyperdimensional vectors and a classifier that classifies these vectors without using multiply and accumulate operators. The patent application provides detailed descriptions and claims for the architecture. [Extracted from the article]
Copyright of Blood Weekly is the property of NewsRx and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Titel: |
Researchers Submit Patent Application, "Reconfigurable, Hyperdimensional Neural Network Architecture", for Approval (USPTO 20240185591).
|
---|---|
Zeitschrift: | Blood Weekly, 2024-06-27, S. 840-840 |
Veröffentlichung: | 2024 |
Medientyp: | serialPeriodical |
ISSN: | 1065-6073 (print) |
Schlagwort: |
|
Sonstiges: |
|