Machine learning with feature obfuscation

    公开(公告)号:US11636334B2

    公开(公告)日:2023-04-25

    申请号:US16545837

    申请日:2019-08-20

    Abstract: A system having multiple devices that can host different versions of an artificial neural network (ANN). In the system, inputs for the ANN can be obfuscated for centralized training of a master version of the ANN at a first computing device. A second computing device in the system includes memory that stores a local version of the ANN and user data for inputting into the local version. The second computing device includes a processor that extracts features from the user data and obfuscates the extracted features to generate obfuscated user data. The second device includes a transceiver that transmits the obfuscated user data. The first computing device includes a memory that stores the master version of the ANN, a transceiver that receives obfuscated user data transmitted from the second computing device, and a processor that trains the master version based on the received obfuscated user data using machine learning.

    Time to live for load commands
    3.
    发明授权

    公开(公告)号:US11199995B2

    公开(公告)日:2021-12-14

    申请号:US16688250

    申请日:2019-11-19

    Abstract: A memory sub-system configured to be responsive to a time to live requirement for load commands from a processor. For example, a load command issued by the processor (e.g., SoC) can include, or be associated with, an optional time to live parameter. The parameter requires that the data at the memory address be available within the time specified by the time to live parameter. When the requested data is currently in the lower speed memory (e.g., NAND flash) and not available in the higher speed memory (e.g., DRAM, NVRAM), the memory subsystem can determine that the data cannot be made available with the specified time and optionally skip the operations and return an error response immediately.

    PAGE TABLE HOOKS TO MEMORY TYPES
    4.
    发明申请

    公开(公告)号:US20210081324A1

    公开(公告)日:2021-03-18

    申请号:US16573527

    申请日:2019-09-17

    Abstract: A computer system includes physical memory devices of different types that store randomly-accessible data in memory of the computer system. In one approach, access to memory in an address space is maintained by an operating system of the computer system. A virtual page is associated with a first memory type. A page table entry is generated to map a virtual address of the virtual page to a physical address in a first memory device of the first memory type. The page table entry is used by a memory management unit to store the virtual page at the physical address.

    METHODS FOR PERFORMING PROCESSING-IN-MEMORY OPERATIONS ON SERIALLY ALLOCATED DATA, AND RELATED MEMORY DEVICES AND SYSTEMS

    公开(公告)号:US20210072986A1

    公开(公告)日:2021-03-11

    申请号:US16717890

    申请日:2019-12-17

    Abstract: Methods, apparatuses, and systems for in- or near-memory processing are described. Strings of bits (e.g., vectors) may be fetched and processed in logic of a memory device without involving a separate processing unit. Operations (e.g., arithmetic operations) may be performed on numbers stored in a bit-serial way during a single sequence of clock cycles. Arithmetic may thus be performed in a single pass as numbers are bits of two or more strings of bits are fetched and without intermediate storage of the numbers. Vectors may be fetched (e.g., identified, transmitted, received) from one or more bit lines. Registers of the memory array may be used to write (e.g., store or temporarily store) results or ancillary bits (e.g., carry bits or carry flags) that facilitate arithmetic operations. Circuitry near, adjacent, or under the memory array may employ XOR or AND (or other) logic to fetch, organize, or operate on the data.

    Distributed machine learning with privacy protection

    公开(公告)号:US11755884B2

    公开(公告)日:2023-09-12

    申请号:US16545813

    申请日:2019-08-20

    CPC classification number: G06N3/045 G06N3/048 G06N20/20

    Abstract: A system having multiple devices that can host different versions of an artificial neural network (ANN). In the system, changes to local versions of the ANN can be combined with a master version of the ANN. In the system, a first device can include memory that can store the master version, a second device can include memory that can store a local version of the ANN, and there can be many devices that store local versions of the ANN. The second device (or any other device of the system hosting a local version) can include a processor that can train the local version, and a transceiver that can transmit changes to the local version generated from the training. The first device can include a transceiver that can receive the changes to a local version, and a processing device that can combine the received changes with the master version.

Patent Agency Ranking