公开(公告)号：US20220067491A1

公开(公告)日：2022-03-03

申请号：US17006602

申请日：2020-08-28

申请人： Micron Technology, Inc.

发明人： Dmitry Vengertsev ,  Stewart R. Watson ,  Jing Gong ,  Ameya Parab

IPC分类号： G06N3/063 ,  G06N3/08 ,  G06N7/00 ,  G06N5/04 ,  G11C13/00 ,  H03M1/36

摘要： Apparatuses and methods can be related to implementing a Bayesian neural network in a memory. A Bayesian neural network can be implemented utilizing a resistive memory array. The memory array can comprise programmable memory cells that can be programed and used to store weights of the Bayesian neural network and perform operations consistent with the Bayesian neural network.

公开(公告)号：US20240289597A1

公开(公告)日：2024-08-29

申请号：US18656130

申请日：2024-05-06

申请人： Micron Technology, Inc.

发明人： Jing Gong ,  Stewart R. Watson ,  Dmitry Vengertsev ,  Ameya Parab

IPC分类号： G06N3/049 ,  G06N3/065 ,  G06N3/084 ,  G06N5/046 ,  G11C13/00 ,  H03M1/12

CPC分类号： G06N3/049 ,  G06N3/065 ,  G06N3/084 ,  G06N5/046 ,  G11C13/0002 ,  H03M1/12

摘要： Apparatuses and methods can be related to implementing a transformer neural network in a memory. A transformer neural network can be implemented utilizing a resistive memory array. The memory array can comprise programmable memory cells that can be programed and used to store weights of the transformer neural network and perform operations consistent with the transformer neural network.

公开(公告)号：US20240185406A1

公开(公告)日：2024-06-06

申请号：US18438256

申请日：2024-02-09

申请人： MICRON TECHNOLOGY, INC.

发明人： Yutao Gong ,  Dmitry Vengertsev ,  Seth A. Eichmeyer ,  Jing Gong

IPC分类号： G06T7/00 ,  G01N21/88 ,  G01N21/95 ,  G06V10/762 ,  G06V10/764 ,  G06V10/776 ,  G06V10/82 ,  H01L21/67

CPC分类号： G06T7/0004 ,  G01N21/9501 ,  G06T7/001 ,  G06V10/762 ,  G06V10/764 ,  G06V10/776 ,  G06V10/82 ,  G01N2021/8887 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30148 ,  H01L21/67288

摘要： An inspection system for determining wafer defects in semiconductor fabrication may include an image capturing device to capture a wafer image and a classification convolutional neural network (CNN) to determine a classification from a plurality of classes for the captured image. Each of the plurality of classes indicates a type of a defect in the wafer. The system may also include an encoder to encode to convert a training image into a feature vector; a cluster system to cluster the feature vector to generate soft labels for the training image; and a decoder to decode the feature vector into a re-generated image. The system may also include a classification system to determine a classification from the plurality of classes for the training image. The encoder and decoder may be formed from a CNN autoencoder. The classification CNN and the CNN autoencoder may each be a deep neural network.

公开(公告)号：US11983619B2

公开(公告)日：2024-05-14

申请号：US16994302

申请日：2020-08-14

申请人： Micron Technology, Inc.

发明人： Jing Gong ,  Stewart R. Watson ,  Dmitry Vengertsev ,  Ameya Parab

IPC分类号： G06N3/049 ,  G06N3/065 ,  G06N3/084 ,  G06N5/046 ,  G11C13/00 ,  H03M1/12

CPC分类号： G06N3/049 ,  G06N3/065 ,  G06N3/084 ,  G06N5/046 ,  G11C13/0002 ,  H03M1/12

摘要： Apparatuses and methods can be related to implementing a transformer neural network in a memory. A transformer neural network can be implemented utilizing a resistive memory array. The memory array can comprise programmable memory cells that can be programed and used to store weights of the transformer neural network and perform operations consistent with the transformer neural network.

公开(公告)号：US11681906B2

公开(公告)日：2023-06-20

申请号：US17006602

申请日：2020-08-28

申请人： Micron Technology, Inc.

发明人： Dmitry Vengertsev ,  Stewart R. Watson ,  Jing Gong ,  Ameya Parab

IPC分类号： G11C11/54 ,  G06N3/063 ,  G06N3/084 ,  H03M1/36 ,  G11C13/00 ,  G06N5/046 ,  G06N7/01

CPC分类号： G06N3/063 ,  G06N3/084 ,  G06N5/046 ,  G06N7/01 ,  G11C11/54 ,  G11C13/004 ,  G11C13/0009 ,  G11C13/0069 ,  H03M1/36

摘要： Apparatuses and methods can be related to implementing a Bayesian neural network in a memory. A Bayesian neural network can be implemented utilizing a resistive memory array. The memory array can comprise programmable memory cells that can be programed and used to store weights of the Bayesian neural network and perform operations consistent with the Bayesian neural network.

公开(公告)号：US11922613B2

公开(公告)日：2024-03-05

申请号：US16925243

申请日：2020-07-09

申请人： MICRON TECHNOLOGY, INC.

发明人： Yutao Gong ,  Dmitry Vengertsev ,  Seth A. Eichmeyer ,  Jing Gong

IPC分类号： G06T7/00 ,  G01N21/95 ,  G06V10/762 ,  G06V10/764 ,  G06V10/776 ,  G06V10/82 ,  G01N21/88 ,  H01L21/67

CPC分类号： G06T7/0004 ,  G01N21/9501 ,  G06T7/001 ,  G06V10/762 ,  G06V10/764 ,  G06V10/776 ,  G06V10/82 ,  G01N2021/8887 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30148 ,  H01L21/67288

摘要： An inspection system for determining wafer defects in semiconductor fabrication may include an image capturing device to capture a wafer image and a classification convolutional neural network (CNN) to determine a classification from a plurality of classes for the captured image. Each of the plurality of classes indicates a type of a defect in the wafer. The system may also include an encoder to encode to convert a training image into a feature vector; a cluster system to cluster the feature vector to generate soft labels for the training image; and a decoder to decode the feature vector into a re-generated image. The system may also include a classification system to determine a classification from the plurality of classes for the training image. The encoder and decoder may be formed from a CNN autoencoder. The classification CNN and the CNN autoencoder may each be a deep neural network.

公开(公告)号：US20220366224A1

公开(公告)日：2022-11-17

申请号：US17319765

申请日：2021-05-13

申请人： Micron Technology, Inc.

发明人： Dmitry Vengertsev ,  Seth A. Eichmeyer ,  Jing Gong ,  John Christopher M. Sancon ,  Nicola Ciocchini ,  Tom Tangelder

IPC分类号： G06N3/063 ,  G06N3/04 ,  G11C11/54 ,  G11C13/00

摘要： Apparatuses and methods can be related to implementing a binary neural network in memory. A binary neural network can be implemented utilizing a resistive memory array. The memory array can comprise programmable memory cells that can be programed and used to store weights of the binary neural network and perform operations consistent with the binary neural network. The weights of the binary neural network can correspond to non-zero values.

公开(公告)号：US20210201460A1

公开(公告)日：2021-07-01

申请号：US16925243

申请日：2020-07-09

申请人： MICRON TECHNOLOGY, INC.

发明人： Yutao Gong ,  Dmitry Vengertsev ,  Seth A. Eichmeyer ,  Jing Gong

IPC分类号： G06T7/00 ,  G01N21/95

摘要： An inspection system for determining wafer defects in semiconductor fabrication may include an image capturing device to capture a wafer image and a classification convolutional neural network (CNN) to determine a classification from a plurality of classes for the captured image. Each of the plurality of classes indicates a type of a defect in the wafer. The system may also include an encoder to encode to convert a training image into a feature vector; a cluster system to cluster the feature vector to generate soft labels for the training image; and a decoder to decode the feature vector into a re-generated image. The system may also include a classification system to determine a classification from the plurality of classes for the training image. The encoder and decoder may he formed from a CNN autoencoder. The classification CNN and the CNN autoencoder may each be a deep neural network.