-
公开(公告)号：US11531695B2
公开(公告)日：2022-12-20
申请号：US16638802
申请日：2018-05-14
Applicant: Google LLC
Inventor： Xiang Wu , David Simcha , Daniel Holtmann-Rice , Sanjiv Kumar , Ananda Theertha Suresh , Ruiqi Guo , Xinnan Yu
Abstract: The present disclosure provides systems and methods that include or otherwise leverage use of a multiscale quantization model that is configured to provide a quantized dataset. In particular, the multiscale quantization model can receive and perform vector quantization of a first dataset. The multiscale quantization model can generate a residual dataset based at least in part on a result of the vector quantization. The multiscale quantization model can apply a rotation matrix to the residual dataset to generate a rotated residual dataset that includes a plurality of rotated residuals. The multiscale quantization model can perform reparameterization of each rotated residual in the rotated residual dataset into a direction component and a scale component. The multiscale quantization model can perform product quantization of the direction components of the plurality of rotated residuals, and perform scalar quantization of the scale components of the plurality of rotated residuals.
-
公开(公告)号：US20210295201A1
公开(公告)日：2021-09-23
申请号：US16821509
申请日：2020-03-17
Applicant: Google LLC
Inventor： Seungyeon Kim , Jingzhao Zhang , Andreas Veit , Sanjiv Kumar , Sashank Reddi , Praneeth Karimireddy
Abstract: 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 per coordinate clipping threshold to clip a current first moment of the coordinate to obtain a current update value that enables faster convergence for the machine-learned model when the noise in the stochastic gradients is heavy tailed.
-
公开(公告)号：US10769529B2
公开(公告)日：2020-09-08
申请号：US16657356
申请日：2019-10-18
Applicant: Google LLC
Inventor： Sashank Jakkam Reddi , Sanjiv Kumar , Manzil Zaheer , Satyen Chandrakant Kale
Abstract: 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.
-
公开(公告)号：US20200183964A1
公开(公告)日：2020-06-11
申请号：US16638802
申请日：2018-05-14
Applicant: Google LLC
Inventor： Xiang Wu , David Simcha , Daniel Holtmann-Rice , Sanjiv Kumar , Ananda Theertha Suresh , Ruiqi Guo , Xinnan Yu
Abstract: The present disclosure provides systems and methods that include or otherwise leverage use of a multiscale quantization model that is configured to provide a quantized dataset. In particular, the multiscale quantization model can receive and perform vector quantization of a first dataset. The multiscale quantization model can generate a residual dataset based at least in part on a result of the vector quantization. The multiscale quantization model can apply a rotation matrix to the residual dataset to generate a rotated residual dataset that includes a plurality of rotated residuals. The multiscale quantization model can perform reparameterization of each rotated residual in the rotated residual dataset into a direction component and a scale component. The multiscale quantization model can perform product quantization of the direction components of the plurality of rotated residuals, and perform scalar quantization of the scale components of the plurality of rotated residuals.
-
公开(公告)号：US20200090031A1
公开(公告)日：2020-03-19
申请号：US16130058
申请日：2018-09-13
Applicant: Google LLC
Inventor： Sashank Jakkam Reddi , Sanjiv Kumar , Satyen Chandrakant Kale
Abstract: 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.
-
Patent Agency Ranking
公开(公告)号：US10262201B2
公开(公告)日：2019-04-16
申请号：US15863299
申请日：2018-01-05
Applicant: GOOGLE LLC
Inventor： Xiaohang Wang , Jeff Huber , Farhan Shamsi , Yakov Okshtein , Sanjiv Kumar , Henry Allan Rowley , Marcus Quintana Mitchell , Debra Lin Repenning
Abstract: 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.
-
公开(公告)号：US20180330180A1
公开(公告)日：2018-11-15
申请号：US16042332
申请日：2018-07-23
Applicant: GOOGLE LLC
Inventor： Xiaohang Wang , Farhan Shamsi , Sanjiv Kumar , Henry Allan Rowley , Marcus Quintana Mitchell
IPC: G06K9/18 , G06K9/00 , G06Q20/36 , G06Q20/34 , G06Q20/32 , G06K7/10 , G06K9/62 , G06K9/22 , G06K9/20 , H04N1/00
CPC classification number: G06K9/186 , G06K7/10 , G06K9/00469 , G06K9/18 , G06K9/2054 , G06K9/228 , G06K9/6202 , G06K2209/01 , G06Q20/32 , G06Q20/3223 , G06Q20/3276 , G06Q20/34 , G06Q20/36 , H04N1/00307
Abstract: Extracting card data comprises receiving, by one or more computing devices, a digital image of a card; perform an image recognition process on the digital representation of the card; identifying an image in the digital representation of the card; comparing the identified image to an image database comprising a plurality of images and determining that the identified image matches a stored image in the image database; determining a card type associated with the stored image and associating the card type with the card based on the determination that the identified image matches the stored image; and performing a particular optical character recognition algorithm on the digital representation of the card, the particular optical character recognition algorithm being based on the determined card type. Another example uses an issuer identification number to improve data extraction. Another example compares extracted data with user data to improve accuracy.
-
公开(公告)号：US12229675B2
公开(公告)日：2025-02-18
申请号：US18081403
申请日：2022-12-14
Applicant: Google LLC
Inventor： Sashank Jakkam Reddi , Sanjiv Kumar , Satyen Chandrakant Kale
Abstract: 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.
-
公开(公告)号：US12001509B2
公开(公告)日：2024-06-04
申请号：US16821509
申请日：2020-03-17
Applicant: Google LLC
Inventor： Seungyeon Kim , Jingzhao Zhang , Andreas Veit , Sanjiv Kumar , Sashank Reddi , Praneeth Karimireddy
CPC classification number: G06F17/18 , G06F18/217 , G06N20/00 , G06N3/084
Abstract: 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 per coordinate clipping threshold to clip a current first moment of the coordinate to obtain a current update value that enables faster convergence for the machine-learned model when the noise in the stochastic gradients is heavy tailed.
-
公开(公告)号：US20230418797A1
公开(公告)日：2023-12-28
申请号：US18341697
申请日：2023-06-26
Applicant: Google LLC
Inventor： Felix Ren-Chyan Chern , Blake Alan Hechtman , Andrew Thomas Davis , Ruiqi Guo , Sanjiv Kumar , David Alexander Majnemer
CPC classification number: G06F16/2237 , G06F16/285
Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for performing a kNN computation using a hardware accelerator. One of the methods includes obtaining a set of one or more query vectors; obtaining a set of database vectors; and performing, on a hardware accelerator and for each query vector in the set, a search for the k most similar database vectors to the query vector, comprising: computing, by circuitry of the hardware accelerator and for each query vector, a respective similarity value between the query vector and each database vector; and for each query vector, identifying, by the hardware accelerator and for each bin, (i) an index of the most similar database vector within the bin and (ii) the respective similarity value for the most similar database vector within the bin.
-
-
-
-
-
-
-
-
-
Search Results
61
records
(took 0.021 seconds)
