Research from National Research Center Yields New Study Findings on Big Data and Cognitive Computing (Extraction of Significant Features by Fixed-Weight Layer of Processing Elements for the Development of an Efficient Spiking Neural Network...).
In: Women's Health Weekly, 2024-01-02, S. 955
serialPeriodical
Zugriff:
A recent study conducted by the National Research Center in Moscow, Russia, has found that fixed-weight layers generated from random distribution or logistic functions can effectively extract significant features from input data, resulting in high accuracy on various tasks. The study specifically focused on datasets such as Fisher's Iris, Wisconsin Breast Cancer, and MNIST. Logistic functions were found to yield high accuracy with less dispersion in results, and the proposed method demonstrated the highest accuracy on Fisher's Iris and MNIST datasets. The research also investigated the impact of non-stochastic spike generation on accuracy. This study provides valuable insights into the development of efficient spiking neural network classifiers. [Extracted from the article]
Copyright of Women's Health 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: |
Research from National Research Center Yields New Study Findings on Big Data and Cognitive Computing (Extraction of Significant Features by Fixed-Weight Layer of Processing Elements for the Development of an Efficient Spiking Neural Network...).
|
---|---|
Zeitschrift: | Women's Health Weekly, 2024-01-02, S. 955 |
Veröffentlichung: | 2024 |
Medientyp: | serialPeriodical |
ISSN: | 1078-7240 (print) |
Sonstiges: |
|