知搜-全球专利检索

  1. 登录
  2. 注册

搜索结果

54 条记录 (耗时 0.02 秒)

    Adaptive Optimization with Improved Convergence
    31.
    发明申请
    Adaptive Optimization with Improved Convergence 审中-公开

    公开(公告)号：US20200090031A1

    公开(公告)日：2020-03-19

    申请号：US16130058

    申请日：2018-09-13

    申请人： Google LLC

    发明人： Sashank Jakkam Reddi ,  Sanjiv Kumar ,  Satyen Chandrakant Kale

    IPC分类号： G06N3/08 ,  G06F15/18 ,  G06F17/16 ,  G06N3/04

    摘要： Generally, the present disclosure is directed to systems and methods that perform adaptive optimization with improved convergence properties. The adaptive optimization techniques described herein are useful in various optimization scenarios, including, for example, training a machine-learned model such as, for example, a neural network. In particular, according to one aspect of the present disclosure, a system implementing the adaptive optimization technique can, over a plurality of iterations, employ an adaptive learning rate while also ensuring that the learning rate is non-increasing.

    Extracting card data from multiple cards
    32.
    发明授权
    Extracting card data from multiple cards 有权

    公开(公告)号：US10262201B2

    公开(公告)日：2019-04-16

    申请号：US15863299

    申请日：2018-01-05

    申请人： GOOGLE LLC

    发明人： Xiaohang Wang ,  Jeff Huber ,  Farhan Shamsi ,  Yakov Okshtein ,  Sanjiv Kumar ,  Henry Allan Rowley ,  Marcus Quintana Mitchell ,  Debra Lin Repenning

    IPC分类号： G06K9/00 ,  G06K9/32 ,  G06K9/20 ,  G06K9/62

    摘要： Extracting financial card information with relaxed alignment comprises a method to receive an image of a card, determine one or more edge finder zones in locations of the image, and identify lines in the one or more edge finder zones. The method further identifies one or more quadrilaterals formed by intersections of extrapolations of the identified lines, determines an aspect ratio of the one or more quadrilateral, and compares the determined aspect ratios of the quadrilateral to an expected aspect ratio. The method then identifies a quadrilateral that matches the expected aspect ratio and performs an optical character recognition algorithm on the rectified model. A similar method is performed on multiple cards in an image. The results of the analysis of each of the cards are compared to improve accuracy of the data.

    Controlled Adaptive Optimization
    35.
    发明公开
    Controlled Adaptive Optimization 审中-公开

    公开(公告)号：US20230394310A1

    公开(公告)日：2023-12-07

    申请号：US18453837

    申请日：2023-08-22

    申请人： Google LLC

    发明人： Sashank Jakkam Reddi ,  Sanjiv Kumar ,  Manzil Zaheer ,  Satyen Chandrakant Kale

    IPC分类号： G06N3/08 ,  G06N3/045

    CPC分类号： G06N3/08 ,  G06N3/045

    摘要： Generally, the present disclosure is directed to systems and methods that perform adaptive optimization with improved convergence properties. The adaptive optimization techniques described herein are useful in various optimization scenarios, including, for example, training a machine-learned model such as, for example, a neural network. In particular, according to one aspect of the present disclosure, a system implementing the adaptive optimization technique can, over a plurality of iterations, employ an adaptive effective learning rate while also ensuring that the effective learning rate is non-increasing.

    Sampled Softmax with Random Fourier Features
    38.
    发明申请
    Sampled Softmax with Random Fourier Features 有权

    公开(公告)号：US20210019654A1

    公开(公告)日：2021-01-21

    申请号：US16931862

    申请日：2020-07-17

    申请人： Google LLC

    发明人： Xinnan Yu ,  Ankit Singh Rawat ,  Jiecao Chen ,  Ananda Theertha Suresh ,  Sanjiv Kumar

    IPC分类号： G06N20/00 ,  G06F40/20 ,  G06K9/62 ,  G06F17/14 ,  G06F17/18

    摘要： Systems and methods for low bias negative sampling of classes according to the sampled softmax method are described herein. The systems and methods can include training a machine-learned model for classifying inputs into one or more classes of a plurality of classes, each of the plurality of classes having an associated class embedding in a plurality of class embeddings. The systems and methods can include selecting, by the one or more computing devices, one or more negative classes from the plurality of classes based at least in part on a probability distribution approximating a softmax distribution, wherein the probability distribution is determined based at least in part on a Random Fourier Features map.

    LOCAL ORTHOGONAL DECOMPOSITION FOR MAXIMUM INNER PRODUCT SEARCH
    39.
    发明申请
    LOCAL ORTHOGONAL DECOMPOSITION FOR MAXIMUM INNER PRODUCT SEARCH 审中-公开

    公开(公告)号：US20200257668A1

    公开(公告)日：2020-08-13

    申请号：US16715620

    申请日：2019-12-16

    申请人： GOOGLE LLC

    发明人： Xiang Wu ,  David Morris Simcha ,  Sanjiv Kumar ,  Ruiqi Guo

    IPC分类号： G06F16/22 ,  G06F16/27 ,  G06F16/2458 ,  G06F16/28 ,  G06F17/16 ,  G06F16/248

    摘要： Techniques of indexing a database and processing a query involve decomposing the residual term according to a projection matrix that is based on a given direction v. For example, for each database element of a partition, the residual for that database element is split into a component parallel to a given direction and a component perpendicular to that direction. The parallel component lies in a one-dimensional subspace spanned by the direction and may be efficiently quantized with a scalar quantization. The perpendicular component is quantized using multiscale quantization techniques. The quantized residual components and the center elements of each partition define the indexed database. Upon receipt of a query from a user, the inner products of q with the residual may be computed efficiently using the quantized residual components. From these inner products, the database elements that are most similar to the query are selected and returned to the user.

    Decreasing neural network inference times using softmax approximation
    40.
    发明授权
    Decreasing neural network inference times using softmax approximation 审中-公开

    公开(公告)号：US10671909B2

    公开(公告)日：2020-06-02

    申请号：US16586702

    申请日：2019-09-27

    申请人： Google LLC

    发明人： Yang Li ,  Sanjiv Kumar ,  Pei-Hung Chen ,  Si Si ,  Cho-Jui Hsieh

    IPC分类号： G06N3/04 ,  G06F17/16 ,  G06F17/18 ,  G06K9/62

    摘要： Methods, systems, and apparatus, including computer programs encoded on computer storage media, for decreasing neural network inference times using softmax approximation. One of the methods includes maintaining data specifying a respective softmax weight vector for each output in a vocabulary of possible neural network outputs; receiving a neural network input; processing the neural network input using one or more initial neural network layers to generate a context vector for the neural network input; and generating an approximate score distribution over the vocabulary of possible neural network outputs for the neural network input, comprising: processing the context vector using a screening model configured to predict a proper subset of the vocabulary for the context input; and generating a respective logit for each output that is in the proper subset, comprising applying the softmax weight vector for the output to the context vector.