公开(公告)号：US12112256B2

公开(公告)日：2024-10-08

申请号：US16982441

申请日：2018-07-26

申请人： Intel Corporation ,  Anbang Yao ,  Aojun Zhou ,  Kuan Wang ,  Hao Zhao ,  Yurong Chen

发明人： Anbang Yao ,  Aojun Zhou ,  Kuan Wang ,  Hao Zhao ,  Yurong Chen

IPC分类号： G06N3/063 ,  G06F18/21 ,  G06F18/214 ,  G06N3/047 ,  G06N3/084

CPC分类号： G06N3/063 ,  G06F18/2148 ,  G06F18/217 ,  G06N3/047 ,  G06N3/084

摘要： Methods, apparatus, systems and articles of manufacture for loss-error-aware quantization of a low-bit neural network are disclosed. An example apparatus includes a network weight partitioner to partition unquantized network weights of a first network model into a first group to be quantized and a second group to be retrained. The example apparatus includes a loss calculator to process network weights to calculate a first loss. The example apparatus includes a weight quantizer to quantize the first group of network weights to generate low-bit second network weights. In the example apparatus, the loss calculator is to determine a difference between the first loss and a second loss. The example apparatus includes a weight updater to update the second group of network weights based on the difference. The example apparatus includes a network model deployer to deploy a low-bit network model including the low-bit second network weights.

公开(公告)号：US20210019630A1

公开(公告)日：2021-01-21

申请号：US16982441

申请日：2018-07-26

申请人： Anbang YAO ,  Aojun ZHOU ,  Kuan WANG ,  Hao ZHAO ,  Yurong CHEN ,  Intel Corporation

发明人： Anbang Yao ,  Aojun Zhou ,  Kuan Wang ,  Hao Zhao ,  Yurong Chen

IPC分类号： G06N3/08 ,  G06K9/62 ,  G06N3/04

摘要： Methods, apparatus, systems and articles of manufacture for loss-error-aware quantization of a low-bit neural network are disclosed. An example apparatus includes a network weight partitioner to partition unquantized network weights of a first network model into a first group to be quantized and a second group to be retrained. The example apparatus includes a loss calculator to process network weights to calculate a first loss. The example apparatus includes a weight quantizer to quantize the first group of network weights to generate low-bit second network weights. In the example apparatus, the loss calculator is to determine a difference between the first loss and a second loss. The example apparatus includes a weight updater to update the second group of network weights based on the difference. The example apparatus includes a network model deployer to deploy a low-bit network model including the low-bit second network weights.

公开(公告)号：US20120034162A1

公开(公告)日：2012-02-09

申请号：US12294991

申请日：2007-03-30

申请人： Andrew R. Barron ,  Jianzhong Yang ,  Jianhua Yang ,  Kuan Wang ,  Jonathan Driver

发明人： Andrew R. Barron ,  Jianzhong Yang ,  Jianhua Yang ,  Kuan Wang ,  Jonathan Driver

IPC分类号： A61K51/08 ,  C07K19/00 ,  C12N5/071 ,  A61K38/02 ,  A61K38/14 ,  A61K9/127 ,  C07K2/00 ,  C07K1/107 ,  B82Y5/00

CPC分类号： C07K7/08 ,  A61K47/645 ,  A61K47/6949 ,  B82Y5/00 ,  C07K1/1077 ,  C07K7/06

摘要： A composition and method is described for intracellular delivery of fullerene containing peptides. The composition and method involve fullerene-substituted phenylalanine as part of a peptide based delivery system. The presence of a fullerene-substituted amino acid in a peptide is found to alter the intracellular transport properties of the peptide.

摘要翻译： 描述了用于含富勒烯的肽的细胞内递送的组合物和方法。 组合物和方法涉及富勒烯取代的苯丙氨酸作为基于肽的递送系统的一部分。 发现肽中富勒烯取代的氨基酸的存在会改变肽的细胞内转运性质。