公开(公告)号：US11710043B2

公开(公告)日：2023-07-25

申请号：US17744601

申请日：2022-05-13

Applicant: Samsung Electronics Co., Ltd.

Inventor： Hui Chen ,  Ilia Ovsiannikov

IPC: G06N3/04 ,  G06N3/082

CPC classification number: G06N3/082 ,  G06N3/04

Abstract: A system and a method of quantizing a pre-trained neural network, includes determining by a layer/channel bit-width determiner for each layer or channel of the pre-trained neural network a minimum quantization noise for the layer or the channel for each master bit-width value in a predetermined set of master bit-width values; and selecting by a bit-width selector for the layer or the channel the master bit-width value having the minimum quantization noise for the layer or the channel. In one embodiment, the minimum quantization noise for the layer or the channel is based on a square of a range of weights for the layer or the channel that is multiplied by a constant to a negative power of a current master bit-width value.

公开(公告)号：US11348009B2

公开(公告)日：2022-05-31

申请号：US16181326

申请日：2018-11-05

Applicant: Samsung Electronics Co., Ltd.

Inventor： Hui Chen ,  Ilia Ovsiannikov

IPC: G06N3/08 ,  G06N3/04

Abstract: A system and a method of quantizing a pre-trained neural network, includes determining by a layer/channel bit-width determiner for each layer or channel of the pre-trained neural network a minimum quantization noise for the layer or the channel for each master bit-width value in a predetermined set of master bit-width values; and selecting by a bit-width selector for the layer or the channel the master bit-width value having the minimum quantization noise for the layer or the channel. In one embodiment, the minimum quantization noise for the layer or the channel is based on a square of a range of weights for the layer or the channel that is multiplied by a constant to a negative power of a current master bit-width value.

公开(公告)号：US12250712B2

公开(公告)日：2025-03-11

申请号：US17717524

申请日：2022-04-11

Applicant: Samsung Electronics Co., Ltd.

Inventor： Meifang Jing ,  Mei Liu ,  Hui Chen ,  Weili Cui ,  Yanyan Qi ,  Zhiqing Zhang

IPC: H04W72/563 ,  H04W72/0446 ,  H04W72/0453 ,  H04W72/20

Abstract: A control resource allocation method, an apparatus, an electronic device, and at least one non-transitory computer readable storage medium are provided. The method includes identifying resource usage status information for the first period, and determining control resource set (CORESET) time-frequency resources and uplink/downlink (UL/DL) control channel element (CCE) patterns for the first period, based on the resource usage status information.

公开(公告)号：US11775611B2

公开(公告)日：2023-10-03

申请号：US16816247

申请日：2020-03-11

Applicant: Samsung Electronics Co., Ltd.

Inventor： Jun Fang ,  Joseph H. Hassoun ,  Ali Shafiee Ardestani ,  Hamzah Ahmed Ali Abdelaziz ,  Georgios Georgiadis ,  Hui Chen ,  David Philip Lloyd Thorsley

IPC: G06F17/18 ,  G06N3/02 ,  G06N3/04 ,  G06N3/08

CPC classification number: G06F17/18 ,  G06N3/02 ,  G06N3/04 ,  G06N3/08

Abstract: In some embodiments, a method of quantizing an artificial neural network includes dividing a quantization range for a tensor of the artificial neural network into a first region and a second region, and quantizing values of the tensor in the first region separately from values of the tensor in the second region. In some embodiments, linear or nonlinear quantization are applied to values of the tensor in the first region and the second region. In some embodiments, the method includes locating a breakpoint between the first region and the second region by substantially minimizing an expected quantization error over at least a portion of the quantization range. In some embodiments, the expected quantization error is minimized by solving analytically and/or searching numerically.