OPTICAL CHANNEL-BASED ELECTRONIC SYSTEMS AND OPERATING METHODS THEREOF

    公开(公告)号:US20240056191A1

    公开(公告)日:2024-02-15

    申请号:US18200145

    申请日:2023-05-22

    CPC classification number: H04B10/506 G02B6/29338

    Abstract: An electronic system for transmitting and receiving internal data through an optical channel. The electronic system may include a light emitter configured to generate a first optical signal, a first device configured to receive the first optical signal and including a transmitter configured to output a second optical signal representing a transmission value based on the first optical signal, a second device including a first receiver configured to receive the second optical signal from the first device and output a third optical signal by adjusting a light intensity of the second optical signal, and configured to read the transmission value based on the light intensity of the second optical signal, and a third device including a second receiver configured to receive the third optical signal from the second device, and configured to read the transmission value based on a light intensity of the third optical signal.

    SYSTEM AND METHOD FOR INCREMENTAL LEARNING
    2.
    发明申请

    公开(公告)号:US20200175384A1

    公开(公告)日:2020-06-04

    申请号:US16255737

    申请日:2019-01-23

    Abstract: Methods, devices, and computer-readable media for incremental learning in image classification and/or object detection. A method for incremental learning includes identifying, for a model for object detection or classification, a first set of object classes the model is trained to detect or classify and adapting the model for use with a second set of object classes different from the first set of object classes to generate an adapted model. The method further includes retaining detection or classification performance on the first set of object classes in the adapted model by performing a knowledge distillation process for the model; and using the adapted model to detect or classify one or more objects from the first set of object classes and one or more objects from the second set of object classes.

    MULTI-TASK BASED LIFELONG LEARNING
    4.
    发明申请

    公开(公告)号:US20200175362A1

    公开(公告)日:2020-06-04

    申请号:US16379704

    申请日:2019-04-09

    Abstract: Methods, devices, and computer-readable media for multi-task based lifelong learning. A method for lifelong learning includes identifying a new task for a machine learning model to perform. The machine learning model trained to perform an existing task. The method includes adaptively training a network architecture of the machine learning model to generate an adapted machine learning model based on incorporating inherent correlations between the new task and the existing task. The method further includes using the adapted machine learning model to perform both the existing task and the new task.

    Optical channel-based electronic systems and operating methods thereof

    公开(公告)号:US12294411B2

    公开(公告)日:2025-05-06

    申请号:US18200145

    申请日:2023-05-22

    Abstract: An electronic system for transmitting and receiving internal data through an optical channel. The electronic system may include a light emitter configured to generate a first optical signal, a first device configured to receive the first optical signal and including a transmitter configured to output a second optical signal representing a transmission value based on the first optical signal, a second device including a first receiver configured to receive the second optical signal from the first device and output a third optical signal by adjusting a light intensity of the second optical signal, and configured to read the transmission value based on the light intensity of the second optical signal, and a third device including a second receiver configured to receive the third optical signal from the second device, and configured to read the transmission value based on a light intensity of the third optical signal.

    Multi-task based lifelong learning

    公开(公告)号:US11775812B2

    公开(公告)日:2023-10-03

    申请号:US16379704

    申请日:2019-04-09

    CPC classification number: G06N3/08 G06N3/04

    Abstract: Methods, devices, and computer-readable media for multi-task based lifelong learning. A method for lifelong learning includes identifying a new task for a machine learning model to perform. The machine learning model trained to perform an existing task. The method includes adaptively training a network architecture of the machine learning model to generate an adapted machine learning model based on incorporating inherent correlations between the new task and the existing task. The method further includes using the adapted machine learning model to perform both the existing task and the new task.

Patent Agency Ranking