中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

53 records (took 0.021 seconds)

    TRAINING NEURAL NETWORKS USING PRIORITY QUEUES
    41.
    发明公开
    TRAINING NEURAL NETWORKS USING PRIORITY QUEUES 审中-公开

    公开(公告)号：US20240127058A1

    公开(公告)日：2024-04-18

    申请号：US18471404

    申请日：2023-09-21

    Applicant: Google LLC

    Inventor： Mohammad Norouzi ,  Daniel Aaron Abolafia ,  Quoc V. Le

    IPC: G06N3/08 ,  G06N3/044

    CPC classification number: G06N3/08 ,  G06N3/044

    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a neural network using a priority queue. One of the methods includes maintaining data identifying a set of K output sequences that were previously generated; selecting at least one of the output sequences from the set of output sequences; for each selected output sequence, determining a respective score; determining, for each selected sequence, a respective first update to the current values of the controller parameters; generating a batch of new output sequences using the controller neural network; obtaining a respective reward for each of the new output sequences; determining, from the new output sequences and the output sequences in the maintained data, the K output sequences that have the highest rewards; and modifying the maintained data.

    Classifying data objects
    42.
    发明授权
    Classifying data objects 有权

    公开(公告)号：US11960519B2

    公开(公告)日：2024-04-16

    申请号：US16998891

    申请日：2020-08-20

    Applicant: Google LLC

    Inventor： Gregory Sean Corrado ,  Tomas Mikolov ,  Samy Bengio ,  Yoram Singer ,  Jonathon Shlens ,  Andrea L Frome ,  Jeffrey Adgate Dean ,  Mohammad Norouzi

    IPC: G06F16/35 ,  G06F16/50

    CPC classification number: G06F16/35 ,  G06F16/50

    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for classifying data objects. One of the methods includes obtaining data that associates each term in a vocabulary of terms with a respective high-dimensional representation of the term; obtaining classification data for a data object, wherein the classification data includes a respective score for each of a plurality of categories, and wherein each of the categories is associated with a respective category label; computing an aggregate high-dimensional representation for the data object from high-dimensional representations for the category labels associated with the categories and the respective scores; identifying a first term in the vocabulary of terms having a high-dimensional representation that is closest to the aggregate high-dimensional representation; and selecting the first term as a category label for the data object.

    Image Enhancement via Iterative Refinement based on Machine Learning Models
    46.
    发明申请
    Image Enhancement via Iterative Refinement based on Machine Learning Models 有权

    公开(公告)号：US20230067841A1

    公开(公告)日：2023-03-02

    申请号：US17391150

    申请日：2021-08-02

    Applicant: Google LLC

    Inventor： Chitwan Saharia ,  Jonathan Ho ,  William Chan ,  Tim Salimans ,  David Fleet ,  Mohammad Norouzi

    IPC: G06T5/00 ,  G06T5/50 ,  G06T3/40 ,  G06N3/08 ,  G06N3/04

    Abstract: A method includes receiving, by a computing device, training data comprising a plurality of pairs of images, wherein each pair comprises an image and at least one corresponding target version of the image. The method also includes training a neural network based on the training data to predict an enhanced version of an input image, wherein the training of the neural network comprises applying a forward Gaussian diffusion process that adds Gaussian noise to the at least one corresponding target version of each of the plurality of pairs of images to enable iterative denoising of the input image, wherein the iterative denoising is based on a reverse Markov chain associated with the forward Gaussian diffusion process. The method additionally includes outputting the trained neural network.

    Systems and Methods for Contrastive Learning of Visual Representations
    47.
    发明申请
    Systems and Methods for Contrastive Learning of Visual Representations 有权

    公开(公告)号：US20210327029A1

    公开(公告)日：2021-10-21

    申请号：US16847163

    申请日：2020-04-13

    Applicant: Google LLC

    Inventor： Ting Chen ,  Simon Kornblith ,  Mohammad Norouzi ,  Geoffrey Everest Hinton

    IPC: G06T5/00 ,  G06T11/00 ,  G06T5/20 ,  G06T7/90 ,  G06T3/40 ,  G06T3/60

    Abstract: Provided are systems and methods for contrastive learning of visual representations. In particular, the present disclosure provides systems and methods that leverage particular data augmentation schemes and a learnable nonlinear transformation between the representation and the contrastive loss to provide improved visual representations. In contrast to certain existing techniques, the contrastive self-supervised learning algorithms described herein do not require specialized architectures or a memory bank. Some example implementations of the proposed approaches can be referred to as a simple framework for contrastive learning of representations or “SimCLR.” Further example aspects are described below and provide the following benefits and insights.

    SYSTEMS AND METHODS FOR CONTRASTIVE LEARNING OF VISUAL REPRESENTATIONS
    48.
    发明申请
    SYSTEMS AND METHODS FOR CONTRASTIVE LEARNING OF VISUAL REPRESENTATIONS 有权

    公开(公告)号：US20210319266A1

    公开(公告)日：2021-10-14

    申请号：US17018372

    申请日：2020-09-11

    Applicant: Google LLC

    Inventor： Ting Chen ,  Simon Kornblith ,  Mohammad Norouzi ,  Geoffrey Everest Hinton

    IPC: G06K9/62 ,  G06N3/08

    Abstract: Systems, methods, and computer program products for performing semi-supervised contrastive learning of visual representations are provided. For example, the present disclosure provides systems and methods that leverage particular data augmentation schemes and a learnable nonlinear transformation between the representation and the contrastive loss to provide improved visual representations. Further, the present disclosure also provides improvements for semi-supervised contrastive learning. For example, computer-implemented method may include performing semi-supervised contrastive learning based on a set of one or more unlabeled training data, generating an image classification model based on a portion of a plurality of layers in a projection head neural network used in performing the contrastive learning, performing fine-tuning of the image classification model based on a set of one or more labeled training data, and after performing the fine-tuning, distilling the image classification model to a student model comprising a relatively smaller number of parameters than the image classification model.

    TRAINING POLICY NEURAL NETWORKS USING PATH CONSISTENCY LEARNING
    49.
    发明申请
    TRAINING POLICY NEURAL NETWORKS USING PATH CONSISTENCY LEARNING 审中-公开

    公开(公告)号：US20200320372A1

    公开(公告)日：2020-10-08

    申请号：US16904785

    申请日：2020-06-18

    Applicant: Google LLC

    Inventor： Ofir Nachum ,  Mohammad Norouzi ,  Dale Eric Schuurmans ,  Kelvin Xu

    IPC: G06N3/04 ,  G06N3/08

    Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training a policy neural network used to select actions to be performed by a reinforcement learning agent interacting with an environment. In one aspect, a method includes obtaining path data defining a path through the environment traversed by the agent. A consistency error is determined for the path from a combined reward, first and last soft-max state values, and a path likelihood. A value update for the current values of the policy neural network parameters is determined from at least the consistency error. The value update is used to adjust the current values of the policy neural network parameters.

    DEVICE PLACEMENT OPTIMIZATION WITH REINFORCEMENT LEARNING
    50.
    发明申请
    DEVICE PLACEMENT OPTIMIZATION WITH REINFORCEMENT LEARNING 审中-公开

    公开(公告)号：US20200279163A1

    公开(公告)日：2020-09-03

    申请号：US16878720

    申请日：2020-05-20

    Applicant: Google LLC

    Inventor： Samuel Bengio ,  Mohammad Norouzi ,  Benoit Steiner ,  Jeffrey Adgate Dean ,  Hieu Hy Pham ,  Azalia Mirhoseini ,  Quoc V. Le ,  Naveen Kumar ,  Yuefeng Zhou ,  Rasmus Munk Larsen

    IPC: G06N3/08 ,  G06N5/04 ,  G06N3/04 ,  G06N3/10

    Abstract: A method for determining a placement for machine learning model operations across multiple hardware devices is described. The method includes receiving data specifying a machine learning model to be placed for distributed processing on multiple hardware devices; generating, from the data, a sequence of operation embeddings, each operation embedding in the sequence characterizing respective operations necessary to perform the processing of the machine learning model; processing the sequence of operation embeddings using a placement recurrent neural network in accordance with first values of a plurality network parameters of the placement recurrent neural network to generate a network output that defines a placement of the operations characterized by the operation embeddings in the sequence across the plurality of devices; and scheduling the machine learning model for processing by the multiple hardware devices by placing the operations on the multiple devices according to the placement defined by the network output.

Patent Agency Ranking