公开(公告)号：US20240119291A1

公开(公告)日：2024-04-11

申请号：US18203552

申请日：2023-05-30

Applicant: NVIDIA Corporation

Inventor： Jose M. Alvarez Lopez ,  Pavlo Molchanov ,  Hongxu Yin ,  Maying Shen ,  Lei Mao ,  Xinglong Sun

IPC: G06N3/082 ,  G06N3/0495

CPC classification number: G06N3/082 ,  G06N3/0495

Abstract: Machine learning is a process that learns a neural network model from a given dataset, where the model can then be used to make a prediction about new data. In order to reduce the size, computation, and latency of a neural network model, a compression technique can be employed which includes model sparsification. To avoid the negative consequences of pruning a fully pretrained neural network model and on the other hand of training a sparse model in the first place without any recovery option, the present disclosure provides a dynamic neural network model sparsification process which allows for recovery of previously pruned parts to improve the quality of the sparse neural network model.

公开(公告)号：US20230077258A1

公开(公告)日：2023-03-09

申请号：US17398673

申请日：2021-08-10

Applicant: Nvidia Corporation

Inventor： Maying Shen ,  Pavlo Molchanov ,  Hongxu Yin ,  Lei Mao ,  Jianna Liu ,  Jose Manuel Alvarez Lopez

IPC: G06N3/08 ,  G06N3/04 ,  G06F11/34

Abstract: Apparatuses, systems, and techniques are presented to simplify neural networks. In at least one embodiment, one or more portions of one or more neural networks are cause to be removed based, at least in part, on one or more performance metrics of the one or more neural networks.