EncodingNet: A Novel Encoding-Based MAC Design for Efficient Neural Network Acceleration

Titel:: EncodingNet: A Novel Encoding-Based MAC Design for Efficient Neural Network Acceleration
Dokumenttyp:: Zeitschriftenaufsatz
Autor(en):: Liu, Bo; Li, Bing; Zhang, Grace Li; Yin, Xunzhao; Zhuo, Cheng; Schlichtmann, Ulf
Stichworte:: Logic; Encoding; Vectors; Circuits; Neural networks; Hardware; Power demand; Artificial intelligence; Systolic arrays; Accuracy; Genetic programming; MAC design; encoding; efficient hardware; neural network acceleration; Cartesian genetic programming
Zeitschriftentitel:: IEEE Transactions on Circuits and Systems for Artificial Intelligence
Jahr:: 2024
Band / Volume:: 1
Heft / Issue:: 2
Seitenangaben Beitrag:: 164-177
Volltext / DOI:: doi:10.1109/TCASAI.2024.3493035
BibTeX