公开(公告)号：US20250077868A1

公开(公告)日：2025-03-06

申请号：US18239198

申请日：2023-08-29

Applicant: ORACLE INTERNATIONAL CORPORATION

Inventor： Baopu LI ,  Tao SHENG ,  Jun QIAN

IPC: G06N3/082 ,  G06N3/0464

Abstract: Systems, methods, and other embodiments associated with contribution metric-based pruning of a neural network are described. In one embodiment, an example method includes accessing a trained neural network that has a plurality of channels. The neural network is to be evaluated for pruning of the channels. The example method may also include determining contribution metrics for the channels by measuring changes in error of the convolutional neural network with individual channels removed in turn. The contribution metrics are determined based at least in part on higher order analysis of the changes. And, the example method may also include pruning out of the convolutional neural network a set of the channels for which the contribution metrics do not satisfy a threshold.