公开(公告)号：US11880763B2

公开(公告)日：2024-01-23

申请号：US16886103

申请日：2020-05-28

Applicant: Intel Corporation

Inventor： Furkan Isikdogan ,  Bhavin V. Nayak ,  Joao Peralta Moreira ,  Chyuan-Tyng Wu ,  Gilad Michael

IPC: G06N3/08 ,  G06V10/70 ,  G06V10/764 ,  G06N3/063 ,  G06F18/214 ,  G06N3/048 ,  G06V10/774 ,  G06V10/776 ,  G06V10/82

CPC classification number: G06N3/08 ,  G06F18/214 ,  G06N3/048 ,  G06N3/063 ,  G06V10/70 ,  G06V10/764 ,  G06V10/774 ,  G06V10/776 ,  G06V10/82

Abstract: An apparatus to facilitate partially-frozen neural networks for efficient computer vision systems is disclosed. The apparatus includes a frozen core to store fixed weights of a machine learning model, one or more trainable cores coupled to the frozen core, the one or more trainable cores comprising multipliers for trainable weights of the machine learning model, and wherein the alpha blending layer includes a trainable alpha blending parameter, and wherein the trainable alpha blending parameter is a function of a trainable parameter, a sigmoid function, and outputs of frozen and trainable blocks in a preceding layer of the machine learning model.

公开(公告)号：US11868892B2

公开(公告)日：2024-01-09

申请号：US17887359

申请日：2022-08-12

Applicant: INTEL CORPORATION

Inventor： Furkan Isikdogan ,  Bhavin V. Nayak ,  Joao Peralta Moreira ,  Chyuan-Tyng Wu ,  Gilad Michael

IPC: G06N3/08 ,  G06V10/70 ,  G06V10/764 ,  G06N3/063 ,  G06F18/214 ,  G06N3/048 ,  G06V10/774 ,  G06V10/776 ,  G06V10/82

CPC classification number: G06N3/08 ,  G06F18/214 ,  G06N3/048 ,  G06N3/063 ,  G06V10/70 ,  G06V10/764 ,  G06V10/774 ,  G06V10/776 ,  G06V10/82

Abstract: An apparatus to facilitate partially-frozen neural networks for efficient computer vision systems is disclosed. The apparatus includes a frozen core to store fixed weights of a machine learning model, one or more trainable cores coupled to the frozen core, the one or more trainable cores comprising multipliers for trainable weights of the machine learning model, and wherein the alpha blending layer includes a trainable alpha blending parameter, and wherein the trainable alpha blending parameter is a function of a trainable parameter, a sigmoid function, and outputs of frozen and trainable blocks in a preceding layer of the machine learning model.

公开(公告)号：US20220391680A1

公开(公告)日：2022-12-08

申请号：US17887359

申请日：2022-08-12

Applicant: INTEL CORPORATION

Inventor： Furkan Isikdogan ,  Bhavin V. Nayak ,  Joao Peralta Moreira ,  Chyuan-Tyng Wu ,  Gilad Michael

IPC: G06N3/063 ,  G06K9/62 ,  G06N3/08 ,  G06N3/04

Abstract: An apparatus to facilitate partially-frozen neural networks for efficient computer vision systems is disclosed. The apparatus includes a frozen core to store fixed weights of a machine learning model, one or more trainable cores coupled to the frozen core, the one or more trainable cores comprising multipliers for trainable weights of the machine learning model, and wherein the alpha blending layer includes a trainable alpha blending parameter, and wherein the trainable alpha blending parameter is a function of a trainable parameter, a sigmoid function, and outputs of frozen and trainable blocks in a preceding layer of the machine learning model.

公开(公告)号：US20200293870A1

公开(公告)日：2020-09-17

申请号：US16886103

申请日：2020-05-28

Applicant: Intel Corporation

Inventor： Furkan Isikdogan ,  Bhavin V. Nayak ,  Joao Peralta Moreira ,  Chyuan-Tyng Wu ,  Gilad Michael

IPC: G06N3/063 ,  G06N3/04 ,  G06N3/08 ,  G06K9/62

Abstract: An apparatus to facilitate partially-frozen neural networks for efficient computer vision systems is disclosed. The apparatus includes a frozen core to store fixed weights of a machine learning model, one or more trainable cores coupled to the frozen core, the one or more trainable cores comprising multipliers for trainable weights of the machine learning model, and wherein the alpha blending layer includes a trainable alpha blending parameter, and wherein the trainable alpha blending parameter is a function of a trainable parameter, a sigmoid function, and outputs of frozen and trainable blocks in a preceding layer of the machine learning model.