Probabilistic in-memory computing

    公开(公告)号:US11900979B2

    公开(公告)日:2024-02-13

    申请号:US17508818

    申请日:2021-10-22

    Abstract: Embodiments of the present disclosure are directed toward probabilistic in-memory computing configurations and arrangements, and configurations of probabilistic bit devices (p-bits) for probabilistic in-memory computing. concept with emerging. A probabilistic in-memory computing device includes an array of p-bits, where each p-bit is disposed at or near horizontal and vertical wires. Each p-bit is a time-varying resistor that has a time-varying resistance, which follows a desired probability distribution. The time-varying resistance of each p-bit represents a weight in a weight matrix of a stochastic neural network. During operation, an input voltage is applied to the horizontal wires to control the current through each p-bit. The currents are accumulated in the vertical wires thereby performing respective multiply-and-accumulative (MAC) operations. Other embodiments may be described and/or claimed.

    MAGNETOELECTRIC LOGIC WITH MAGNETIC TUNNEL JUNCTIONS

    公开(公告)号:US20230100649A1

    公开(公告)日:2023-03-30

    申请号:US17485265

    申请日:2021-09-24

    Abstract: Magnetoelectric magnetic tunnel junction (MEMTJ) logic devices comprise a magnetoelectric switching capacitor coupled to a pair of magnetic tunnel junctions (MTJs) by an insulating layer. The logic state of the MEMTJ is represented by the magnetization orientation of the ferromagnetic layer of the magnetoelectric capacitor and can be switched through the application of an input voltage to the MEMTJ that causes the magnetoelectric switching capacitor to switch states. The magnetization orientation of the magnetoelectric capacitor ferromagnetic layer is read out by the MTJs. The magnetization orientation of a ferromagnetic free layer common to the MTJs is coupled to the ferromagnetic layer of the magnetoelectric capacitor. The potential of the ferromagnetic free layer is based on the power supply voltage applied to the ferromagnetic reference layer of the MTJ having a magnetization orientation parallel to that of the ferromagnetic free layer.

    STAGED OSCILLATORS FOR NEURAL COMPUTING
    9.
    发明申请

    公开(公告)号:US20200372333A1

    公开(公告)日:2020-11-26

    申请号:US16989371

    申请日:2020-08-10

    Abstract: Disclosed herein are staged oscillators for neural computing, as well as related methods and assemblies. In some embodiments, neural computing circuitry may include a first oscillator set, a second oscillator set, and an averaging structure coupled between the first oscillator set and the second oscillator set.

Patent Agency Ranking