- 专利标题： SYSTEMS AND METHODS FOR NEURAL NETWORK TRAINING WITH WEIGHT SPARSITY
-
申请号： US17866194申请日： 2022-07-15
-
公开(公告)号： US20230306257A1公开(公告)日： 2023-09-28
- 发明人: Fei SUN , Minghai QIN , Haoran LI , Guocai ZHU , Yuan GAO , Guyue HUANG , Yawen ZHANG
- 申请人： Alibaba (China) Co., Ltd.
- 申请人地址： CN Hangzhou
- 专利权人： Alibaba (China) Co., Ltd.
- 当前专利权人： Alibaba (China) Co., Ltd.
- 当前专利权人地址： CN Hangzhou
- 优先权： CN 2210289171.5 2022.03.22
- 主分类号： G06N3/08
- IPC分类号： G06N3/08 ; G06F7/78 ; G06F7/523
摘要：
Neural network (NN) model training techniques can include computing activations in a forward pass using a sparse weight matrix that is transpose invariant. The neural network (NN) model training techniques can further include computing activation gradients and weight gradients in a backward pass using the sparse weight matrix.
信息查询
