公开(公告)号：US20220222533A1

公开(公告)日：2022-07-14

申请号：US17317900

申请日：2021-05-12

Applicant: Korea Advanced Institute of Science and Technology

Inventor： Hoi Jun YOO ,  Sang Yeob KIM

IPC: G06N3/08 ,  G06N3/063 ,  G06F9/50 ,  G06F15/80

Abstract: A method of accelerating training of a low-power, high-performance artificial neural network (ANN) includes (a) performing fine-grained pruning and coarse-grained pruning to generate sparsity in weights by a pruning unit in a convolution core of a cluster in a lower-power, high-performance ANN trainer; (b) selecting and performing dual zero skipping according to input sparsity, output sparsity, and the sparsity of weights by the convolution core, and (c) restricting access to a weight memory during training by allowing a deep neural network (DNN) computation core and a weight pruning core to share weights retrieved from a memory by the convolution core.