DEVICES AND METHODS FOR ACCESSING RESISTIVE CHANGE ELEMENTS IN RESISTIVE CHANGE ELEMENT ARRAYS

    公开(公告)号:US20190115054A1

    公开(公告)日:2019-04-18

    申请号:US15783622

    申请日:2017-10-13

    申请人: Nantero, Inc.

    发明人: Jia Luo

    摘要: Devices and methods for accessing resistive change elements in a resistive change element array to determine resistive states of the resistive change elements are disclosed. According to some aspects of the present disclosure the devices and methods access resistive change elements in a resistive change element array through a variety of operations. According to some aspects of the present disclosure the devices and methods supply an amount of current tailored for a particular operation. According to some aspects of the present disclosure the devices and methods compensate for circuit conditions of a resistive change element array by adjusting an amount of current tailored for a particular operation to compensate for circuit conditions of the resistive change element array.

    Methods for error correction with resistive change element arrays

    公开(公告)号:US10261861B2

    公开(公告)日:2019-04-16

    申请号:US15621788

    申请日:2017-06-13

    申请人: Nantero, Inc.

    发明人: Sheyang Ning

    摘要: Error correction methods for arrays of resistive change elements are disclosed. An array of resistive change elements is organized into a plurality of subsections. Each subsection includes at least one flag bit and a plurality of data bits. At the start of a write operation, all bits in a subsection are initialized. If any data bits fail to initialize, the pattern of errors is compared to the input data pattern. The flag cells are then activated to indicate the appropriate encoding pattern to apply to the input data to match the errors. The input data is then encoded according to this encoding pattern before being written to the array. A second error correction algorithm can be used to correct remaining errors. During a read operation, the encoding pattern indicated by the flag bits is used to decode the read data and retrieve the original input data.

    Methods for reading and programming 1-R resistive change element arrays
    17.
    发明授权
    Methods for reading and programming 1-R resistive change element arrays 有权
    读取和编程1-R电阻变化元件阵列的方法

    公开(公告)号:US09299430B1

    公开(公告)日:2016-03-29

    申请号:US14603037

    申请日:2015-01-22

    申请人: Nantero Inc.

    IPC分类号: G11C11/00 G11C13/00 G11C11/56

    摘要: Methods for reading and programming one or more resistive change elements within a 1-R resistive change element array are disclosed. These methods include using measurement and storage elements to measure the electrical response of one or more selected cells within an array and then comparing that stored electrical response to the electrical response of a reference element within the array to determine the resistive state of the one or more selected cells. These methods also include programming methods wherein selectable current limiting elements are used to permit or inhibit programming currents from flowing through selected and unselected cells, respectively. These methods further include programming methods that use specific biasing of array lines to provide sufficient programming currents through only selected cells.

    摘要翻译: 公开了用于读取和编程1-R电阻变化元件阵列内的一个或多个电阻变化元件的方法。 这些方法包括使用测量和存储元件来测量阵列内的一个或多个所选择的单元的电响应,然后将该存储的电响应与该阵列内的参考元件的电响应进行比较,以确定一个或多个 选定的单元格。 这些方法还包括编程方法,其中可选择的电流限制元件分别用于允许或禁止编程电流流过选定和未选择的单元。 这些方法还包括使用阵列线的特定偏置以通过仅选择的单元提供足够的编程电流的编程方法。

    Carbon nanotube-based neural networks and methods of making and using same
    19.
    发明授权
    Carbon nanotube-based neural networks and methods of making and using same 有权
    基于碳纳米管的神经网络及其制造和使用方法

    公开(公告)号:US08659940B2

    公开(公告)日:2014-02-25

    申请号:US12934545

    申请日:2009-03-25

    IPC分类号: G11C11/54

    CPC分类号: G06N3/063

    摘要: Physical neural networks based nanotechnology include dendrite circuits that comprise non-volatile nanotube switches. A first terminal of the non-volatile nanotube switches is able to receive an electrical signal and a second terminal of the non-volatile nanotube switches is coupled to a common node that sums any electrical signals at the first terminals of the nanotube switches. The neural networks further includes transfer circuits to propagate the electrical signal, synapse circuits, and axon circuits.

    摘要翻译: 基于物理神经网络的纳米技术包括包含非挥发性纳米管开关的枝晶电路。 非挥发性纳米管开关的第一端子能够接收电信号,并且非易失性纳米管开关的第二端子耦合到公共节点,该公共节点与纳米管开关的第一端子处的任何电信号相加。 神经网络还包括传输电路以传播电信号,突触电路和轴突电路。