Energy efficient machine learning models

    公开(公告)号:US11620499B2

    公开(公告)日:2023-04-04

    申请号:US16694442

    申请日:2019-11-25

    Abstract: Aspects described herein provide a method including: receiving input data at a machine learning model, comprising: a plurality of processing layers; a plurality of gate logics; a plurality of gates; and a fully connected layer; determining based on a plurality of gate parameters associated with the plurality of gate logics, a subset of the plurality of processing layers with which to process the input data; processing the input data with the subset of the plurality of processing layers and the fully connected layer to generate an inference; determining a prediction loss based on the inference and a training label associated with the input data; determining an energy loss based on the subset of the plurality of processing layers used to process the input data; and optimizing the machine learning model based on: the prediction loss; the energy loss; and a prior probability associated with the training label.

    Accumulate across stages in machine learning object detection

    公开(公告)号:US11176490B2

    公开(公告)日:2021-11-16

    申请号:US16119668

    申请日:2018-08-31

    Abstract: Apparatus, methods, systems, and instructions stored on computer-readable medium are presented for performing classification. A hardware engine may be configurable to implement multiple stages of a cascade classifier including a first stage and a second stage. The hardware engine may be configurable to (a) access a value indicative of whether to accumulate, and (b) responsive to the value indicative of whether to accumulate meeting a continue evaluation condition, (i) access a first numeric value obtained from evaluation of the first stage of the cascade classifier, (ii) accumulate the first numeric value with a second numeric value obtained from evaluation of the second stage of the cascade classifier to generate an accumulated value, and (iii) utilize the accumulated value to determine an outcome for the second stage of the cascade classifier.

    Low power change detection and reduction of sensor power

    公开(公告)号:US11089218B2

    公开(公告)日:2021-08-10

    申请号:US16592678

    申请日:2019-10-03

    Abstract: Methods, systems, and devices for change detection are described. The methods, systems, and devices relate to monitoring a field of view of an image sensor via a first pixel associated with a group of pixels of the image sensor, where a dimension of the first pixel exceeds a dimension of at least one pixel of the group of pixels of the image sensor, detecting a change in the field of view of the image sensor based on the monitoring, and activating a second pixel of the image sensor based on detecting the change in the field of view of the image sensor.

    Low power data generation for iris-related detection and authentication

    公开(公告)号:US10984235B2

    公开(公告)日:2021-04-20

    申请号:US15713561

    申请日:2017-09-22

    Abstract: Sensing of scene-based occurrences is disclosed. In one example, a vision sensor system comprises (1) dedicated computer vision (CV) computation hardware configured to receive sensor data from at least one sensor array and capable of computing CV features using readings from multiple neighboring sensor pixels and (2) a first processing unit communicatively coupled with the dedicated CV computation hardware. The vision sensor system is configured to, in response to processing of the one or more computed CV features indicating a presence of one or more irises in a scene captured by the at least one sensor array, generate data in support of iris-related operations to be performed by a second processing unit and send the generated data to the second processing unit.

    REAL-WORLD TRAFFIC MODEL
    38.
    发明申请

    公开(公告)号:US20200326203A1

    公开(公告)日:2020-10-15

    申请号:US16549643

    申请日:2019-08-23

    Abstract: Disclosed is a method and apparatus for generating a real-world traffic model. The apparatus obtains a first set of device map information associated with one or more devices that are in proximity with a first device, and obtains a second set of device map information associated with one or more devices that are in proximity with a second device. The apparatus determines whether the first set of device map information and the second set of device map information contain at least one common device and in response to the determination that the first set of device map information and the second set of device map information contain at least one common device, and generates a real-world traffic model of devices based on the first set of device map information and the second set of device map information.

    BANDWIDTH INFORMATION DETERMINATION FOR FLEXIBLE BANDWIDTH CARRIERS

    公开(公告)号:US20180376361A1

    公开(公告)日:2018-12-27

    申请号:US16107303

    申请日:2018-08-21

    Abstract: Methods, systems, and devices for wireless communication are provided for mobility management for wireless communications systems that utilize a flexible bandwidth carrier. Some embodiments include approaches for determining bandwidth information, such as one or more bandwidth scaling factors N and/or flexible bandwidths, at a user equipment (UE), where the bandwidth information may not be signaled to the UE. Embodiments for determining bandwidth information include: random ordered bandwidth scaling factor approaches, delay ordered bandwidth scaling factor approaches, storing bandwidth scaling factor value in UE Neighbor Record approaches, spectrum measurement approaches, spectrum calculation approaches, and/or a priori approaches. Flexible bandwidth carrier systems may utilize spectrum portions that may not be big enough to fit a normal waveform. Flexible bandwidth carrier systems may be generated through dilating, or scaling down, time, frame lengths, bandwidth, or the chip rate of the flexible bandwidth carrier systems with respect to a normal bandwidth carrier system.

Patent Agency Ranking