中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

14 records (took 0.032 seconds)

    NEURAL NETWORK ARCHITECTURE FOR IMPLEMENTING GROUP CONVOLUTIONS
    1.
    发明申请
    NEURAL NETWORK ARCHITECTURE FOR IMPLEMENTING GROUP CONVOLUTIONS 有权

    公开(公告)号：US20250124700A1

    公开(公告)日：2025-04-17

    申请号：US18694626

    申请日：2021-10-08

    Applicant: Google LLC

    Inventor： Berkin Akin ,  Suyog Gupta ,  Cao Gao ,  Ping Zhou ,  Gabriel Mintzer Bender ,  Hanxiao Liu

    IPC: G06V10/82 ,  G06V10/77 ,  G06V10/94

    Abstract: Methods, systems, and apparatus, including computer-readable media, are described for processing an input image using a convolutional neural network (CNN). The CNN includes a sequence of layer blocks. Each of a first subset of the layer blocks in the sequence is configured to perform operations that include: i) receiving an input feature map for the layer block, ii) generating an expanded feature map from the input feature map using a group convolution, and iii) generating a reduced feature map from the expanded feature map. The input feature map is an h w feature map with c1 channels. The expanded feature map is an h w feature map with c2 channels, whereas the reduced feature map is an h w feature map with c1 channels. C2 is greater than c1. An output feature map is generated for the layer block from the reduced feature map.

    Systems and Methods for Machine-Learned Models Having Convolution and Attention
    2.
    发明申请
    Systems and Methods for Machine-Learned Models Having Convolution and Attention 有权

    公开(公告)号：US20220383069A1

    公开(公告)日：2022-12-01

    申请号：US17827130

    申请日：2022-05-27

    Applicant: Google LLC

    Inventor： Zihang Dai ,  Hanxiao Liu ,  Mingxing Tan ,  Quoc V. Le

    IPC: G06N3/04 ,  G06N3/08 ,  G06N3/063 ,  G06N20/00

    Abstract: A computer-implemented method for performing computer vision with reduced computational cost and improved accuracy can include obtaining, by a computing system including one or more computing devices, input data comprising an input tensor having one or more dimensions, providing, by the computing system, the input data to a machine-learned convolutional attention network, the machine-learned convolutional attention network including two or more network stages, and, in response to providing the input data to the machine-learned convolutional attention network, receiving, by the computing system, a machine-learning prediction from the machine-learned convolutional attention network. The convolutional attention network can include at least one attention block, wherein the attention block includes a relative attention mechanism, the relative attention mechanism including the sum of a static convolution kernel with an adaptive attention matrix. This provides for improved generalization, capacity, and efficiency of the convolutional attention network relative to some existing models.

    ATTENTION NEURAL NETWORKS WITH GATED ATTENTION UNITS
    3.
    发明申请
    ATTENTION NEURAL NETWORKS WITH GATED ATTENTION UNITS 有权

    公开(公告)号：US20250139431A1

    公开(公告)日：2025-05-01

    申请号：US18834202

    申请日：2023-01-30

    Applicant: Google LLC

    Inventor： Hanxiao Liu ,  Weizhe Hua ,  Zihang Dai ,  Quoc V. Le

    IPC: G06N3/08 ,  G06N3/048

    Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for performing a machine learning task on a network input to generate a network output. In one aspect, one of the systems includes a neural network configured to perform the machine learning task, the neural network including one or more attentive layers that each include a gated attention unit.

    HARDWARE ACCELERATOR OPTIMIZED GROUP CONVOLUTION BASED NEURAL NETWORK MODELS
    5.
    发明申请
    HARDWARE ACCELERATOR OPTIMIZED GROUP CONVOLUTION BASED NEURAL NETWORK MODELS 有权

    公开(公告)号：US20240386260A1

    公开(公告)日：2024-11-21

    申请号：US18693724

    申请日：2021-10-08

    Applicant: Google LLC

    Inventor： Berkin Akin ,  Suyog Gupta ,  Cao Gao ,  Ping Zhou ,  Gabriel Mintzer Bender ,  Hanxiao Liu

    IPC: G06N3/063 ,  G06N3/0464 ,  G06V10/77 ,  G06V10/82 ,  G06V10/94

    Abstract: Methods, systems, and apparatus, including computer-readable media, are described for processing an input image using integrated circuit that implements a convolutional neural network with a group convolution layer. The processing includes determining a mapping of partitions along a channel dimension of an input feature map to multiply accumulate cells (MACs) in a computational unit of the circuit and applying a group convolution to the input feature map. Applying the group convolution includes, for each partition: providing weights for the group convolution layer to a subset of MACs based on the mapping; providing, via an input bus of the circuit, an input of the feature map to each MAC in the subset; and computing, at each MAC in the subset, a product using the input and a weight for the group convolution layer. An output feature map is generated for the group convolution layer based on an accumulation of products.

    LEARNED GRAPH OPTIMIZATIONS FOR COMPILERS
    6.
    发明公开
    LEARNED GRAPH OPTIMIZATIONS FOR COMPILERS 审中-公开

    公开(公告)号：US20230176840A1

    公开(公告)日：2023-06-08

    申请号：US17921933

    申请日：2021-06-07

    Applicant: Google LLC

    Inventor： Yanqi Zhou ,  Sudip Roy ,  Amirali Abdolrashidi ,  Daniel Lin-Kit Wong ,  Chao Ma ,  Qiumin Xu ,  Hanxiao Liu ,  Phitchaya Mangpo Phothilimthana ,  Shen Wang ,  Anna Darling Goldie ,  Azalia Mirhoseini ,  James Laudon

    IPC: G06F8/41

    CPC classification number: G06F8/443

    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for compiler optimizations using a compiler optimization network. One of the methods includes receiving an input program, wherein the input program defines a graph of operation modules, wherein each node in the graph is a respective operation module, and each edge between nodes in the graph represents one operation module receiving the output generated by another operation module. The input program is processed by a compiler optimization network comprising a graph-embedding network that is configured to encode operation features and operation dependencies of the operation modules of the input program into a graph embedding representation and a policy network that is configured to generate an optimization action for each of one or more nodes encoded in the graph embedding representation. The compiler optimization network generates an output optimization plan comprising one or more optimization actions for the input program.

    Systems and Methods for Machine-Learned Models Having Convolution and Attention
    8.
    发明公开
    Systems and Methods for Machine-Learned Models Having Convolution and Attention 审中-公开

    公开(公告)号：US20230359862A1

    公开(公告)日：2023-11-09

    申请号：US18355243

    申请日：2023-07-19

    Applicant: Google LLC

    Inventor： Zihang Dai ,  Mingxing Tan ,  Quoc V. Le ,  Hanxiao Liu

    IPC: G06N3/044 ,  G06N20/00 ,  G06N3/063 ,  G06N3/08

    CPC classification number: G06N3/044 ,  G06N20/00 ,  G06N3/063 ,  G06N3/08

    Abstract: A computer-implemented method for performing computer vision with reduced computational cost and improved accuracy can include obtaining, by a computing system including one or more computing devices, input data comprising an input tensor having one or more dimensions, providing, by the computing system, the input data to a machine-learned convolutional attention network, the machine-learned convolutional attention network including two or more network stages, and, in response to providing the input data to the machine-learned convolutional attention network, receiving, by the computing system, a machine-learning prediction from the machine-learned convolutional attention network. The convolutional attention network can include at least one attention block, wherein the attention block includes a relative attention mechanism, the relative attention mechanism including the sum of a static convolution kernel with an adaptive attention matrix. This provides for improved generalization, capacity, and efficiency of the convolutional attention network relative to some existing models.

    SEARCHING FOR NORMALIZATION-ACTIVATION LAYER ARCHITECTURES
    9.
    发明申请
    SEARCHING FOR NORMALIZATION-ACTIVATION LAYER ARCHITECTURES 有权

    公开(公告)号：US20230121404A1

    公开(公告)日：2023-04-20

    申请号：US17798046

    申请日：2021-02-08

    Applicant: Google LLC

    Inventor： Hanxiao Liu ,  Quoc V. Le ,  Andrew Brock ,  Karen Simonyan

    IPC: G06N3/08 ,  G06N3/04

    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for searching for an architecture for an activation-normalization layer to be included in a neural network to replace a set of layers that receive a layer input comprising a plurality of values, apply one or more normalization operations to the values in the layer input to generate a normalized layer input, and apply an element-wise activation function to the normalized layer input to generate a layer output.

Patent Agency Ranking