Fast Fourier Transform (FFT) custom address generator

    公开(公告)号:US09846678B2

    公开(公告)日:2017-12-19

    申请号:US15068849

    申请日:2016-03-14

    Applicant: Apple Inc.

    CPC classification number: G06F17/142 G11C8/04

    Abstract: An apparatus and method for Fast Fourier Transform (FFT) address generation is disclosed. The apparatus may include a counter circuit and circuitry configured to load an initial value into a counter circuit. The circuitry may be further configured to generate first and second output values by formatting a current value of the counter, and increment the current value of the counter circuit by an increment value to generate a next value. The circuitry may also be configured to modify the increment value in response to a determination that the next value is equal to a target value.

    Using proxies to enable on-device machine learning

    公开(公告)号:US11210583B2

    公开(公告)日:2021-12-28

    申请号:US15275355

    申请日:2016-09-24

    Applicant: Apple Inc.

    Abstract: Systems and methods are disclosed for a server generating a plurality of proxy prediction models for each of a plurality of applications for use by client devices. Providing a prediction model based on a data distribution that more closely matches the user private data of the actual user of the client device, as opposed to a generic model, can improve the accuracy of predictions and improve the benefits to the user of the client device. The plurality of prediction models are generated by a server and provided to a plurality of clients. For a particular application, a client device can use previously collected private user data to select one of the plurality of prediction models for the application as being a closest matching prediction model to use for a particular user.

    USING PROXIES TO ENABLE ON-DEVICE MACHINE LEARNING

    公开(公告)号:US20180025287A1

    公开(公告)日:2018-01-25

    申请号:US15275355

    申请日:2016-09-24

    Applicant: Apple Inc.

    CPC classification number: G06N20/00 G06N5/04

    Abstract: Systems and methods are disclosed for a server generating a plurality of proxy prediction models for each of a plurality of applications for use by client devices. Providing a prediction model based on a data distribution that more closely matches the user private data of the actual user of the client device, as opposed to a generic model, can improve the accuracy of predictions and improve the benefits to the user of the client device. The plurality of prediction models are generated by a server and provided to a plurality of clients. For a particular application, a client device can use previously collected private user data to select one of the plurality of prediction models for the application as being a closest matching prediction model to use for a particular user.

    FAST FOURIER TRANSFORM (FFT) CUSTOM ADDRESS GENERATOR

    公开(公告)号:US20170091147A1

    公开(公告)日:2017-03-30

    申请号:US15068849

    申请日:2016-03-14

    Applicant: Apple Inc.

    CPC classification number: G06F17/142 G11C8/04

    Abstract: An apparatus and method for Fast Fourier Transform (FFT) address generation is disclosed. The apparatus may include a counter circuit and circuitry configured to load an initial value into a counter circuit. The circuitry may be further configured to generate first and second output values by formatting a current value of the counter, and increment the current value of the counter circuit by an increment value to generate a next value. The circuitry may also be configured to modify the increment value in response to a determination that the next value is equal to a target value.

Patent Agency Ranking