中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

39 records (took 0.019 seconds)

    OTS-based dynamic storage structure and operation method thereof
    2.
    发明授权
    OTS-based dynamic storage structure and operation method thereof 有权

    公开(公告)号：US12249373B2

    公开(公告)日：2025-03-11

    申请号：US18033075

    申请日：2022-01-25

    Applicant: HUAZHONG UNIVERSITY OF SCIENCE AND TECHNOLOGY

    Inventor： Hao Tong ,  Binhao Wang ,  Xiangshui Miao

    IPC: G11C11/16 ,  G11C13/00

    Abstract: Disclosed are an OTS-based dynamic storage structure and an operation method thereof. The OTS-based dynamic storage structure includes a plurality of storage units distributed in an array, and each storage unit includes an OTS gating transistor and a storage capacitor. The OTS gating transistor has two states, namely, high resistance state and low resistance state. When the voltage across the OTS gating transistor exceeds the threshold voltage Vth, the OTS gating transistor is switched from the high resistance state to the low resistance state. When the voltage across the OTS gating transistor in the low resistance state is lower than the holding voltage Vhold, the OTS gating transistor is switched from the low resistance state to the high resistance state.

    Convolutional neural network on-chip learning system based on non-volatile memory
    4.
    发明授权
    Convolutional neural network on-chip learning system based on non-volatile memory 有权

    公开(公告)号：US11861489B2

    公开(公告)日：2024-01-02

    申请号：US16961932

    申请日：2019-07-12

    Applicant: HUAZHONG UNIVERSITY OF SCIENCE AND TECHNOLOGY

    Inventor： Xiangshui Miao ,  Yi Li ,  Wenqian Pan

    IPC: G06N3/065 ,  G06N3/04 ,  G06N3/08 ,  G06F17/15

    CPC classification number: G06N3/065 ,  G06F17/153 ,  G06N3/04 ,  G06N3/08

    Abstract: Disclosed by the disclosure is a convolutional neural network on-chip learning system based on non-volatile memory, comprising: an input module, a convolutional neural network module, an output module and a weight update module. The on-chip learning of the convolutional neural network module implements the synaptic function by using the characteristic of the memristor, and the convolutional kernel value or synaptic weight value is stored in a memristor unit; the input module converts the input signal into the voltage signal; the convolutional neural network module converts the input voltage signal layer-by-layer, and transmits the result to the output module to obtain the output of the network; and the weight update module adjusts the conductance value of the memristor in the convolutional neural network module according to the result of the output module to update the network convolutional kernel value or synaptic weight value.

    Non-volatile logic device based on phase-change magnetic materials and logic operation method thereof
    6.
    发明授权
    Non-volatile logic device based on phase-change magnetic materials and logic operation method thereof 有权
    基于相变磁性材料的非易失性逻辑器件及其逻辑运算方法

    公开(公告)号：US09543955B2

    公开(公告)日：2017-01-10

    申请号：US14849621

    申请日：2015-09-10

    Applicant: Huazhong University of Science and Technology

    Inventor： Xiangshui Miao ,  Yi Li ,  Yingpeng Zhong

    IPC: H03K19/08 ,  G11C11/16 ,  G11C13/00 ,  H03K19/177 ,  G11B5/02 ,  H03K19/18

    CPC classification number: H03K19/08 ,  G11B5/02 ,  G11C11/16 ,  G11C11/161 ,  G11C11/1673 ,  G11C11/1675 ,  G11C13/0004 ,  G11C13/004 ,  G11C13/0097 ,  H03K19/1776 ,  H03K19/18

    Abstract: A non-volatile logic device, including: a substrate, a magnetic head, a base electrode, an insulating layer, a phase-change magnetic film, and a top electrode. The substrate includes a silicon substrate and an active layer attached to the silicon substrate. The base electrode includes an N-type silicon layer, a P-type silicon layer and a heating layer, the N-type silicon layer and the P-type silicon layer constitute a PN diode structure, and the size of the heating layer is smaller than that of the P-type silicon layer. The phase-change magnetic film is deposited on the insulating layer and is electrically contacted with the heating layer. The top electrode and the base electrode are connected to an external electrical pulse signal, and an external magnetic field parallel to a two dimensional plane of the phase-change magnetic film is applied to the non-volatile logic device.

    Abstract translation: 一种非易失性逻辑器件，包括：基板，磁头，基极，绝缘层，相变磁性膜和顶部电极。 衬底包括硅衬底和附着到硅衬底的有源层。 基极包括N型硅层，P型硅层和加热层，N型硅层和P型硅层构成PN二极管结构，加热层的尺寸较小 比P型硅层高。 相变磁性膜沉积在绝缘层上并与加热层电接触。 顶部电极和基极连接到外部电脉冲信号，并且将平行于相变磁性膜的二维平面的外部磁场施加到非易失性逻辑器件。

    Convolution operation accelerator and convolution operation method
    7.
    发明授权
    Convolution operation accelerator and convolution operation method 有权

    公开(公告)号：US12293804B2

    公开(公告)日：2025-05-06

    申请号：US18266610

    申请日：2022-04-20

    Applicant: HUAZHONG UNIVERSITY OF SCIENCE AND TECHNOLOGY

    Inventor： Xiangshui Miao ,  Jiawei Fu ,  Yuhui He

    IPC: G11C5/02 ,  G06N3/0464 ,  G11C5/06 ,  G06N3/045 ,  G06N3/063

    Abstract: The disclosure provides a convolution operation accelerator and a convolution operation method and belongs to the field of microelectronic devices. Input data of each word line may be subjected to a multiply-accumulate operation together with two upper and lower layers of convolution kernel units, so that natural sliding of the convolution kernel units in a y direction in two-dimensional input is achieved. The oblique bit lines and multiple copies of a convolution kernel in each layer of a non-volatile memory array may enable a multiplication operation between one piece of input data and convolution kernel data at different positions in the same convolution kernel. In this way, the natural sliding of the convolution kernel units in an x direction in the two-dimensional input is achieved.

    Method and system of designing memristor-based naive Bayes classifier and classifier
    8.
    发明授权
    Method and system of designing memristor-based naive Bayes classifier and classifier 有权

    公开(公告)号：US12266152B2

    公开(公告)日：2025-04-01

    申请号：US17775591

    申请日：2021-05-07

    Applicant: HUAZHONG UNIVERSITY OF SCIENCE AND TECHNOLOGY

    Inventor： Huajun Sun ,  Zuopai Zhou ,  Li Li ,  Xiangshui Miao

    IPC: G06V10/84 ,  G06N3/06 ,  G06V10/764 ,  G06V10/94

    Abstract: A method and a system of designing a memristor-based naive Bayes classifier and a classifier belonging to the field of information technology are provided. The method includes: constructing a naive Bayes classifier including a memristor array of M rows by 2N columns, where M is the number of classification types, and N is the number of pixels in a picture; calculating the number hj,2i-1 of the pixel value of 0 and the number hj,2i of the pixel value of 1 in an ith pixel in the jth training sample, where j=1, 2, . . . , and M; and applying hj,2i-1 pulses to a memristor Rj,2i-1 in a jth row and a 2i-1th column to modulate the conductance of the memristor Rj,2i-1 and applying hj,2i pulses to a memristor Rj,2i in the jth row and a 2ith column to modulate the conductance of the memristor Rj,2i.

    Chalcogenide phase change material based all-optical switch and manufacturing method therefor
    9.
    发明授权
    Chalcogenide phase change material based all-optical switch and manufacturing method therefor 有权

    公开(公告)号：US11609443B2

    公开(公告)日：2023-03-21

    申请号：US16764403

    申请日：2018-06-07

    Applicant: HUAZHONG UNIVERSITY OF SCIENCE AND TECHNOLOGY

    Inventor： Xiangshui Miao ,  Yitao Lu ,  Hao Tong ,  Yi Wang

    IPC: G02F1/01 ,  G02B1/00 ,  G02F1/00

    Abstract: Disclosed in the present invention are a chalcogenide phase change material based all-optical switch and a manufacturing method therefor, relating to the field of optical communications. The all-optical switch comprises: stacked in sequence, a cover layer film, a chalcogenide phase change material film, an isolation layer film, a silicon photonic crystal, and a substrate. The silicon photonic crystal comprises a nano-porous structure such that the silicon photonic crystal has a Fano resonance effect. When the all-optical switch is used, the state of the chalcogenide phase change material film is controlled by means of laser, and the resonance state of the silicon photonic crystal is modulated to implement modulation of signal light transmissivity; the modulation range is within a communication band from 1500 nm to 1600 nm, thereby implementing an optical switch. The all-optical switch of the present invention has the characteristics of high contrast ratio, high rate and low loss.

    Operating method for improving performance of selector device
    10.
    发明授权
    Operating method for improving performance of selector device 有权

    公开(公告)号：US11437098B2

    公开(公告)日：2022-09-06

    申请号：US17037655

    申请日：2020-09-29

    Applicant: HUAZHONG UNIVERSITY OF SCIENCE AND TECHNOLOGY

    Inventor： Xiangshui Miao ,  Qi Lin ,  Hao Tong

    IPC: G11C11/00 ,  G11C13/00

    Abstract: An operating method for improving the performance of a selector device is provided, including: determining and applying a direct current (DC) or alternating current (AC) operating voltage and a limit current of the selector device, so that the selector device circulates until a off-state resistance is reduced; continuously applying the operating voltage and the limit current to the selector device, so that the selector device circulates until the off-state resistance is reduced to a minimum value; continuously applying the operating voltage and the limit current to the selector device, so that the selector device circulates until the off-state resistance is increased; continuously applying the operating voltage and the limit current to the selector device, so that the selector device circulates until the off-state resistance is increased to a maximum value; and adjusting the operating voltage and the limit current, and performing DC or AC operation pulsed operation on a selector.

Patent Agency Ranking