中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

32 records (took 0.028 seconds)

    SEQUENCE MODELING USING IMPUTATION
    3.
    发明申请
    SEQUENCE MODELING USING IMPUTATION 有权

    公开(公告)号：US20230075716A1

    公开(公告)日：2023-03-09

    申请号：US17797872

    申请日：2021-02-08

    Applicant: Google LLC

    Inventor： William Chan ,  Chitwan Saharia ,  Geoffrey E. Hinton ,  Mohammad Norouzi ,  Navdeep Jaitly

    IPC: G06F40/47 ,  G06F40/284

    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for sequence modeling. One of the methods includes receiving an input sequence having a plurality of input positions; determining a plurality of blocks of consecutive input positions; processing the input sequence using a neural network to generate a latent alignment, comprising, at each of a plurality of input time steps: receiving a partial latent alignment from a previous input time step; selecting an input position in each block, wherein the token at the selected input position of the partial latent alignment in each block is a mask token; and processing the partial latent alignment and the input sequence using the neural network to generate a new latent alignment, wherein the new latent alignment comprises, at the selected input position in each block, an output token or a blank token; and generating, using the latent alignment, an output sequence.

    TRAINING DISTILLED MACHINE LEARNING MODELS
    4.
    发明申请
    TRAINING DISTILLED MACHINE LEARNING MODELS 有权

    公开(公告)号：US20220351091A1

    公开(公告)日：2022-11-03

    申请号：US17863733

    申请日：2022-07-13

    Applicant: Google LLC

    Inventor： Oriol Vinyals ,  Jeffrey Adgate Dean ,  Geoffrey E. Hinton

    IPC: G06N20/20 ,  G06N7/00 ,  G06N20/00 ,  G06N3/04 ,  G06N3/08

    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a distilled machine learning model. One of the methods includes training a cumbersome machine learning model, wherein the cumbersome machine learning model is configured to receive an input and generate a respective score for each of a plurality of classes; and training a distilled machine learning model on a plurality of training inputs, wherein the distilled machine learning model is also configured to receive inputs and generate scores for the plurality of classes, comprising: processing each training input using the cumbersome machine learning model to generate a cumbersome target soft output for the training input; and training the distilled machine learning model to, for each of the training inputs, generate a soft output that matches the cumbersome target soft output for the training input.

    NEURAL NETWORK TRAINING USING THE SOFT NEAREST NEIGHBOR LOSS
    5.
    发明申请
    NEURAL NETWORK TRAINING USING THE SOFT NEAREST NEIGHBOR LOSS 有权

    公开(公告)号：US20220101624A1

    公开(公告)日：2022-03-31

    申请号：US17423612

    申请日：2020-01-22

    Applicant: Google LLC

    Inventor： Geoffrey E. Hinton ,  Nicholas Myles Wisener Frosst ,  Nicolas Guy Robert Papernot

    IPC: G06V10/774 ,  G06N3/04

    Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training a classification neural network. In one aspect, a method comprises: for each of a plurality of network inputs: processing the network input using the classification neural network to generate a classification output that defines a predicted class of the network input; determining a soft nearest neighbor loss, wherein the soft nearest neighbor loss encourages intermediate representations of network inputs of different classes to become more entangled, wherein the entanglement of intermediate representations of network inputs of different classes characterizes how similar pairs of intermediate representations of network inputs of different class are relative to pairs of intermediate representations of network inputs of the same class; and adjusting the current values of the classification neural network parameters using gradients of the soft nearest neighbor loss with respect to the classification neural network parameters.

    OBJECT DISCOVERY IN IMAGES THROUGH CATEGORIZING OBJECT PARTS
    9.
    发明申请
    OBJECT DISCOVERY IN IMAGES THROUGH CATEGORIZING OBJECT PARTS 有权

    公开(公告)号：US20220230425A1

    公开(公告)日：2022-07-21

    申请号：US17613767

    申请日：2020-05-22

    Applicant: Google LLC

    Inventor： Adam Roman Kosiorek ,  Geoffrey E. Hinton ,  Sara Sabour Rouh Aghdam ,  Yee Whye Teh

    IPC: G06V10/82 ,  G06V10/40 ,  G06T7/70

    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for detecting objects in images. One of the methods includes obtaining an input image; processing the input image to generate predicted part feature data, the predicted part feature data comprising, for each of a plurality of possible object parts: a part presence probability representing a likelihood that the possible object part is depicted in the input image, a predicted pose of the possible object part in the input image given that the possible object part is depicted in the input image, and an object part feature vector characterizing the depiction of the possible object part given that the possible object part is depicted in the input image; and processing the predicted part feature data for the plurality of possible object parts to generate an object detection output that identifies one or more objects depicted in the input image.

Patent Agency Ranking