- 专利标题： TECHNIQUE FOR HARDWARE ACTIVATION FUNCTION COMPUTATION IN RNS ARTIFICIAL NEURAL NETWORKS
-
申请号： US18193635申请日： 2023-03-31
-
公开(公告)号： US20230385115A1公开(公告)日： 2023-11-30
- 发明人: Athanasios STOURAITIS , Sakellariou VASILEIOS , Vasileios PALIOURAS , Ioannis KOURETAS , Hani SALEH
- 申请人： Khalifa University of Science and Technology
- 申请人地址： AE Abu Dhabi
- 专利权人： Khalifa University of Science and Technology
- 当前专利权人： Khalifa University of Science and Technology
- 当前专利权人地址： AE Abu Dhabi
- 优先权： GR 220100431 2022.05.24
- 主分类号： G06F9/50
- IPC分类号： G06F9/50 ; G06F7/72
摘要：
A device can be used to implement a neural network in hardware. The device can include a processor, a memory, and a neural network accelerator. The neural network accelerator can be configured to implement, in hardware, a neural network by using a residue number system (RNS). At least one function of the neural network can have a corresponding approximation in the RNS system, and the at least one function can be provided by implementing the corresponding approximation in hardware.
信息查询
