利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

20 条记录 (耗时 0.017 秒)

    Data compression using integer neural networks
    1.
    发明授权
    Data compression using integer neural networks 有权

    公开(公告)号：US11869221B2

    公开(公告)日：2024-01-09

    申请号：US17274596

    申请日：2019-09-18

    申请人： Google LLC

    发明人： Nicholas Johnston ,  Johannes Balle

    IPC分类号： G06T9/00 ,  G06F17/18 ,  G06N3/084 ,  G06N3/045

    CPC分类号： G06T9/002 ,  G06F17/18 ,  G06N3/045 ,  G06N3/084

    摘要： Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for reliably performing data compression and data decompression across a wide variety of hardware and software platforms by using integer neural networks. In one aspect, there is provided a method for entropy encoding data which defines a sequence comprising a plurality of components, the method comprising: for each component of the plurality of components: processing an input comprising: (i) a respective integer representation of each of one or more components of the data which precede the component in the sequence, (ii) an integer representation of one or more respective latent variables characterizing the data, or (iii) both, using an integer neural network to generate data defining a probability distribution over the predetermined set of possible code symbols for the component of the data.

    Tiled image compression using neural networks
    2.
    发明授权
    Tiled image compression using neural networks 有权

    公开(公告)号：US11250595B2

    公开(公告)日：2022-02-15

    申请号：US16617484

    申请日：2018-05-29

    申请人： GOOGLE LLC

    发明人： Michele Covell ,  Damien Vincent ,  David Charles Minnen ,  Saurabh Singh ,  Sung Jin Hwang ,  Nicholas Johnston ,  Joel Eric Shor ,  George Dan Toderici

    IPC分类号： G06T9/00 ,  G06N3/04 ,  G06N3/08 ,  G06T3/40 ,  G06T7/00

    摘要： Methods, systems, and apparatus, including computer programs encoded on computer storage media, for image compression and reconstruction. An image encoder system receives a request to generate an encoded representation of an input image that has been partitioned into a plurality of tiles and generates the encoded representation of the input image. To generate the encoded representation, the system processes a context for each tile using a spatial context prediction neural network that has been trained to process context for an input tile and generate an output tile that is a prediction of the input tile. The system determines a residual image between the particular tile and the output tile generated by the spatial context prediction neural network by process the context for the particular tile and generates a set of binary codes for the particular tile by encoding the residual image using an encoder neural network.

    DATA COMPRESSION USING INTEGER NEURAL NETWORKS
    3.
    发明公开
    DATA COMPRESSION USING INTEGER NEURAL NETWORKS 审中-公开

    公开(公告)号：US20240104786A1

    公开(公告)日：2024-03-28

    申请号：US18520975

    申请日：2023-11-28

    申请人： Google LLC

    发明人： Nicholas Johnston ,  Johannes Balle

    IPC分类号： G06T9/00 ,  G06F17/18 ,  G06N3/045 ,  G06N3/084

    CPC分类号： G06T9/002 ,  G06F17/18 ,  G06N3/045 ,  G06N3/084

    摘要： Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for reliably performing data compression and data decompression across a wide variety of hardware and software platforms by using integer neural networks. In one aspect, there is provided a method for entropy encoding data which defines a sequence comprising a plurality of components, the method comprising: for each component of the plurality of components: processing an input comprising: (i) a respective integer representation of each of one or more components of the data which precede the component in the sequence, (ii) an integer representation of one or more respective latent variables characterizing the data, or (iii) both, using an integer neural network to generate data defining a probability distribution over the predetermined set of possible code symbols for the component of the data.

    LOOK-UP TABLE BASED NEURAL NETWORKS
    5.
    发明申请
    LOOK-UP TABLE BASED NEURAL NETWORKS 审中-公开

    公开(公告)号：US20200234126A1

    公开(公告)日：2020-07-23

    申请号：US16751175

    申请日：2020-01-23

    申请人： Google LLC

    发明人： Michele Covell ,  David Marwood ,  Shumeet Baluja ,  Nicholas Johnston

    IPC分类号： G06N3/08 ,  G06N3/04 ,  G06F1/03

    摘要： Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing a network input using a neural network to generate a network output for the network input. One of the methods includes maintaining, for each of the plurality of neural network layers, a respective look-up table that maps each possible combination of a quantized input index and a quantized weight index to a multiplication result; and generating a network output from a network input, comprising, for each of the neural network layers: receiving data specifying a quantized input to the neural network layer, the quantized input comprising a plurality of quantized input values; and generating a layer output for the neural network layer from the quantized input to the neural network layer using the respective look-up table for the neural network layer.

    Look-up table based neural networks
    6.
    发明授权
    Look-up table based neural networks 有权

    公开(公告)号：US12118466B2

    公开(公告)日：2024-10-15

    申请号：US17978026

    申请日：2022-10-31

    申请人： Google LLC

    发明人： Michele Covell ,  David Marwood ,  Shumeet Baluja ,  Nicholas Johnston

    IPC分类号： G06F1/03 ,  G06N3/048 ,  G06N3/08

    CPC分类号： G06N3/08 ,  G06F1/03 ,  G06N3/048

    摘要： Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing a network input using a neural network to generate a network output for the network input. One of the methods includes maintaining, for each of the plurality of neural network layers, a respective look-up table that maps each possible combination of a quantized input index and a quantized weight index to a multiplication result; and generating a network output from a network input, comprising, for each of the neural network layers: receiving data specifying a quantized input to the neural network layer, the quantized input comprising a plurality of quantized input values; and generating a layer output for the neural network layer from the quantized input to the neural network layer using the respective look-up table for the neural network layer.

    LOOK-UP TABLE BASED NEURAL NETWORKS
    7.
    发明公开
    LOOK-UP TABLE BASED NEURAL NETWORKS 审中-公开

    公开(公告)号：US20230186082A1

    公开(公告)日：2023-06-15

    申请号：US17978026

    申请日：2022-10-31

    申请人： Google LLC

    发明人： Michele Covell ,  David Marwood ,  Shumeet Baluja ,  Nicholas Johnston

    IPC分类号： G06N3/08 ,  G06F1/03 ,  G06N3/048

    CPC分类号： G06N3/08 ,  G06F1/03 ,  G06N3/048

    摘要： Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing a network input using a neural network to generate a network output for the network input. One of the methods includes maintaining, for each of the plurality of neural network layers, a respective look-up table that maps each possible combination of a quantized input index and a quantized weight index to a multiplication result; and generating a network output from a network input, comprising, for each of the neural network layers: receiving data specifying a quantized input to the neural network layer, the quantized input comprising a plurality of quantized input values; and generating a layer output for the neural network layer from the quantized input to the neural network layer using the respective look-up table for the neural network layer.

    Learning compressible features
    8.
    发明授权
    Learning compressible features 有权

    公开(公告)号：US11610124B2

    公开(公告)日：2023-03-21

    申请号：US16666689

    申请日：2019-10-29

    申请人： Google LLC

    发明人： Abhinav Shrivastava ,  Saurabh Singh ,  Johannes Balle ,  Sami Ahmad Abu-El-Haija ,  Nicholas Johnston ,  George Dan Toderici

    IPC分类号： G06K9/00 ,  G06N3/082 ,  G06F17/15 ,  G06K9/62 ,  G06N3/063

    摘要： Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for receiving, by a neural network (NN), a dataset for generating features from the dataset. A first set of features is computed from the dataset using at least a feature layer of the NN. The first set of features i) is characterized by a measure of informativeness; and ii) is computed such that a size of the first set of features is compressible into a second set of features that is smaller in size than the first set of features and that has a same measure of informativeness as the measure of informativeness of the first set of features. The second set of features if generated from the first set of features using a compression method that compresses the first set of features to generate the second set of features.

    Data compression using conditional entropy models
    9.
    发明授权
    Data compression using conditional entropy models 有权

    公开(公告)号：US11257254B2

    公开(公告)日：2022-02-22

    申请号：US16515586

    申请日：2019-07-18

    申请人： Google LLC

    发明人： David Charles Minnen ,  Saurabh Singh ,  Johannes Balle ,  Troy Chinen ,  Sung Jin Hwang ,  Nicholas Johnston ,  George Dan Toderici

    IPC分类号： G06T9/00 ,  G06N20/00 ,  G06F17/18 ,  G06N3/08 ,  G06T3/40

    摘要： Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for compressing and decompressing data. In one aspect, a method comprises: processing data using an encoder neural network to generate a latent representation of the data; processing the latent representation of the data using a hyper-encoder neural network to generate a latent representation of an entropy model; generating an entropy encoded representation of the latent representation of the entropy model; generating an entropy encoded representation of the latent representation of the data using the latent representation of the entropy model; and determining a compressed representation of the data from the entropy encoded representations of: (i) the latent representation of the data and (ii) the latent representation of the entropy model used to entropy encode the latent representation of the data.