Resource-aware training for neural networks

    公开(公告)号:US11551093B2

    公开(公告)日:2023-01-10

    申请号:US16254406

    申请日:2019-01-22

    Applicant: Adobe Inc.

    Abstract: In implementations of resource-aware training for neural network, one or more computing devices of a system implement an architecture optimization module for monitoring parameter utilization while training a neural network. Dead neurons of the neural network are identified as having activation scales less than a threshold. Neurons with activation scales greater than or equal to the threshold are identified as survived neurons. The dead neurons are converted to reborn neurons by adding the dead neurons to layers of the neural network having the survived neurons. The reborn neurons are prevented from connecting to the survived neurons for training the reborn neurons.

    Resource-Aware Training for Neural Networks
    2.
    发明申请

    公开(公告)号:US20200234128A1

    公开(公告)日:2020-07-23

    申请号:US16254406

    申请日:2019-01-22

    Applicant: Adobe Inc.

    Abstract: In implementations of resource-aware training for neural network, one or more computing devices of a system implement an architecture optimization module for monitoring parameter utilization while training a neural network. Dead neurons of the neural network are identified as having activation scales less than a threshold. Neurons with activation scales greater than or equal to the threshold are identified as survived neurons. The dead neurons are converted to reborn neurons by adding the dead neurons to layers of the neural network having the survived neurons. The reborn neurons are prevented from connecting to the survived neurons for training the reborn neurons.

    CONVOLUTIONAL NEURAL NETWORKS WITH ADJUSTABLE FEATURE RESOLUTIONS AT RUNTIME

    公开(公告)号:US20210232927A1

    公开(公告)日:2021-07-29

    申请号:US16751897

    申请日:2020-01-24

    Applicant: Adobe Inc.

    Abstract: In some embodiments, an application receives a request to execute a convolutional neural network model. The application determines the computational complexity requirement for the neural network based on the computing resource available on the device. The application further determines the architecture of the convolutional neural network model by determining the locations of down-sampling layers within the convolutional neural network model based on the computational complexity requirement. The application reconfigures the architecture of the convolutional neural network model by moving the down-sampling layers to the determined locations and executes the convolutional neural network model to generate output results.

    COMPRESSION OF MACHINE LEARNING MODELS

    公开(公告)号:US20210073644A1

    公开(公告)日:2021-03-11

    申请号:US16563226

    申请日:2019-09-06

    Applicant: Adobe Inc.

    Abstract: A machine learning model compression system and related techniques are described herein. The machine learning model compression system can intelligently remove certain parameters of a machine learning model, without introducing a loss in performance of the machine learning model. Various parameters of a machine learning model can be removed during compression of the machine learning model, such as one or more channels of a single-branch or multi-branch neural network, one or more branches of a multi-branch neural network, certain weights of a channel of a single-branch or multi-branch neural network, and/or other parameters. In some cases, compression is performed only on certain selected layers or branches of the machine learning model. Candidate filters from the selected layers or branches can be removed from the machine learning model in a way that preserves local features of the machine learning model.

    Convolutional neural networks with adjustable feature resolutions at runtime

    公开(公告)号:US12079725B2

    公开(公告)日:2024-09-03

    申请号:US16751897

    申请日:2020-01-24

    Applicant: Adobe Inc.

    CPC classification number: G06N3/082 G06N20/00

    Abstract: In some embodiments, an application receives a request to execute a convolutional neural network model. The application determines the computational complexity requirement for the neural network based on the computing resource available on the device. The application further determines the architecture of the convolutional neural network model by determining the locations of down-sampling layers within the convolutional neural network model based on the computational complexity requirement. The application reconfigures the architecture of the convolutional neural network model by moving the down-sampling layers to the determined locations and executes the convolutional neural network model to generate output results.

    Resource-aware training for neural networks

    公开(公告)号:US11790234B2

    公开(公告)日:2023-10-17

    申请号:US18063851

    申请日:2022-12-09

    Applicant: Adobe Inc.

    CPC classification number: G06N3/082 G06N3/04 G06F18/2148

    Abstract: In implementations of resource-aware training for neural network, one or more computing devices of a system implement an architecture optimization module for monitoring parameter utilization while training a neural network. Dead neurons of the neural network are identified as having activation scales less than a threshold. Neurons with activation scales greater than or equal to the threshold are identified as survived neurons. The dead neurons are converted to reborn neurons by adding the dead neurons to layers of the neural network having the survived neurons. The reborn neurons are prevented from connecting to the survived neurons for training the reborn neurons.

Patent Agency Ranking