公开(公告)号：WO2022074570A1

公开(公告)日：2022-04-14

申请号：PCT/IB2021/059141

申请日：2021-10-05

Applicant: KHALIFA UNIVERSITY OF SCIENCE AND TECHNOLOGY

Inventor： TOLBA, Mohammed F. ,  SALEH, Hani ,  AL-QUTAYRI, Mahmoud ,  MOHAMMAD, Baker

IPC: G06N3/063 ,  G06N3/08 ,  G06N3/04 ,  G06F7/544 ,  G06F17/15 ,  G06F17/16 ,  G06F17/18 ,  G06F1/3234

Abstract: A method can be used to reduce the memory storage and energy used by deep neural networks. The method can include determining the weights associated with the deep neural network. An input feature map can be received and used with the weights to generate approximated weights. Using the approximated weights and the input feature map a convolution inference can be performed.