公开(公告)号：US20250021826A1

公开(公告)日：2025-01-16

申请号：US18629162

申请日：2024-04-08

Applicant: Samsung Electronics Co., Ltd.

Inventor： Shangqian Gao ,  Ting Hua ,  Yen-Chang Hsu ,  Yilin Shen ,  Hongxia Jin

IPC: G06N3/0985 ,  G06N3/0495

Abstract: In one embodiment, a method includes accessing at least a portion of a training dataset for a trained neural network that includes multiple layers, where each layer includes a number of parameters, and where the training dataset includes multiple training samples that each include an input and a ground-truth output used to train the trained neural network. The method further includes training a hypernetwork to generate a layer-specific compression mask for each of one or more of the multiple layers of the trained neural network. The method further includes generating, by the trained hypernetwork, a final layer-specific compression mask for the trained neural network and compressing the trained neural network by reducing, for each of the one or more layers of the neural network, the number of parameters of that layer according to the final layer-specific compression mask.

公开(公告)号：US20250029005A1

公开(公告)日：2025-01-23

申请号：US18669413

申请日：2024-05-20

Applicant: Samsung Electronics Co., Ltd.

Inventor： Ting Hua ,  Xiao Li ,  Shangqian Gao ,  Yen-Chang Hsu ,  Yilin Shen ,  Hongxia Jin

IPC: G06N20/00 ,  G10L15/18 ,  G10L15/26

Abstract: A method includes accessing a plurality of weight matrices of a machine learning model. The method also includes, for each weight matrix, decomposing the weight matrix into a U matrix, an S matrix, and a V matrix using singular value decomposition. The S matrix is a diagonal matrix, and a singular group corresponds to each element in the S matrix. The method further includes, for each weight matrix, determining an importance score of each singular group. The importance score of the singular group represents a change in loss if the singular group is removed from the machine learning model. The method also includes, for each weight matrix, ranking the singular groups across the plurality of weight matrices based on the importance scores. In addition, the method includes, for each weight matrix, identifying one or more of the singular groups to prune based on the ranking of the singular groups.