Analysis of Posit and Bfloat Arithmetic of Real Numbers for Machine Learning

Analysis of Posit and Bfloat Arithmetic of Real Numbers for Machine Learning

Modern computational tasks are often required to not only guarantee predefined accuracy, but get the result fast. Optimizing calculations using floating point numbers, as opposed to integers, is a non-trivial task. For this reason, there is a need to explore new ways to improve such operations. This...

Full description

Bibliographic Details
Main Authors: Aleksandr Yu. Romanov, Alexander L. Stempkovsky, Ilia V. Lariushkin, Georgy E. Novoselov, Roman A. Solovyev, Vladimir A. Starykh, Irina I. Romanova, Dmitry V. Telpukhov, Ilya A. Mkrtchan
Format: Article
Language:English
Published: IEEE 2021-01-01
Series:IEEE Access
Subjects:
Machine learning
floating point
posit
IEEE 754
benchmark
Online Access:https://ieeexplore.ieee.org/document/9446981/

Internet

https://ieeexplore.ieee.org/document/9446981/

Similar Items