JOURNAL ARTICLE

Delta-Sigma Domain Signal Processing Applied to Artificial Neurons.

  • Published In: Journal of Multiple-Valued Logic & Soft Computing, 2025, v. 45, n. 1-3. P. 249 1 of 3

  • Database: Applied Science & Technology Source Ultimate 2 of 3

  • Authored By: TAKAO WAHO; AKIHISA KOYAMA; HITOSHI HAYASHI 3 of 3

Abstract

First- and second-order delta-sigma () modulated bitstreams are applied to implement the multiply-and-accumulate (MAC) operation and the rectified linear unit (ReLU) activation function. Our simulation shows that the numerical accuracy is improved by using -modulated bitstreams compared to the bitstreams used in stochastic computing (SC). This improvement is due to the noise shaping properties inherent in modulation. Specifically, we found that for both MAC and ReLU, the root mean square error (RMSE) can be reduced in proportion to the inverse of N3/2 and N5/2 by employing first- and second-order modulation as the bitstream length N increases. This demonstrates the superiority of the modulation over the conventional SC in terms of achieving higher numerical accuracy with shorter bitstream lengths. [ABSTRACT FROM AUTHOR]

Additional Information

  • Source:Journal of Multiple-Valued Logic & Soft Computing. 2025/06, Vol. 45, Issue 1-3, p249
  • Document Type:Article
  • Subject Area:Engineering
  • Publication Date:2025
  • ISSN:15423980
  • Accession Number:186002096
  • Copyright Statement:Copyright of Journal of Multiple-Valued Logic & Soft Computing is the property of Old City Publishing, Inc. and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. 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.)

Looking to go deeper into this topic? Look for more articles on EBSCOhost.