-
公开(公告)号：US10474926B1
公开(公告)日：2019-11-12
申请号：US15815492
申请日：2017-11-16
Applicant: Amazon Technologies, Inc.
Inventor： Leo Parker Dirac , Vineet Khare , Gurumurthy Swaminathan , Xiong Zhou
Abstract: Features related to systems and methods expediting generation of a machine learning model, such as an image recognition model, are described. Existing machine learning models are analyzed to identify a starting point for creating the new machine learning model. An existing machine learning model can suggest learning parameters (e.g., training parameters or structural features of the model) that can be used to expedite the generating and training process along with training data that can augment the training of the new machine learning model.
-
公开(公告)号：US10467729B1
公开(公告)日：2019-11-05
申请号：US15782390
申请日：2017-10-12
Applicant: Amazon Technologies, Inc.
Inventor： Pramuditha Hemanga Perera , Gurumurthy Swaminathan , Vineet Khare
Abstract: A method and system for a deep learning-based approach to image processing to increase a level of optical zooming and increasing the resolution associated with a captured image. The system includes an image capture device to generate a display of a field of view (e.g., of a scene within a viewable range of a lens of the image capture device). An indication of a desired zoom level (e.g., 1.1× to 5×) is received, and, based on this selection, a portion of the field of view is cropped. In one embodiment, the cropped portion displayed by the image capture device for a user's inspection, prior to the capturing of a low resolution image. The low resolution image is provided to an artificial neural network trained to apply a resolution up-scaling model to transform the low resolution image to a high resolution image of the cropped portion.
-
公开(公告)号：US11605021B1
公开(公告)日：2023-03-14
申请号：US16588245
申请日：2019-09-30
Applicant: Amazon Technologies, Inc.
Inventor： Vineet Khare , Saurabh Gupta , Yijie Zhuang , Bharathan Balaji , Runfei Luo , Siddhartha Agarwal
Abstract: Techniques for iterative model training and deployment for automated learning systems are described. A method of iterative model training and deployment for automated learning systems comprises generating training data based on inference data, provided by a first version of a model hosted at an endpoint of a machine learning service, and feedback data, received from a client application, using an identifier associated with the inference data and the feedback data, generating a second version of the model using the training data, and deploying the model to the endpoint of the machine learning service.
-
公开(公告)号：US11249827B2
公开(公告)日：2022-02-15
申请号：US16799443
申请日：2020-02-24
Applicant: Amazon Technologies, Inc.
Inventor： Vineet Khare , Alexander Johannes Smola , Craig Wiley
Abstract: Techniques for providing and servicing listed repository items such as algorithms, data, models, pipelines, and/or notebooks are described. In some examples, web services provider receives a request for a listed repository item from a requester, the request indicating at least a category of the repository item and each listing of a repository item includes an indication of a category that the listed repository item belongs to and a storage location of the listed repository item, determines a suggestion of at least one listed repository item based on the request, and provides the suggestion of the at least one listed repository item to the requester.
-
公开(公告)号：US10394913B1
公开(公告)日：2019-08-27
申请号：US15210841
申请日：2016-07-14
Applicant: Amazon Technologies, Inc.
Inventor： Vineet Shashikant Chaoji , Sivaramakrishnan Kaveri , Vineet Khare , Gourav Roy , Saurabh Sohoney , Andrew Dennis Willingham
IPC: G06F16/00 , G06F16/9535 , G06F7/24 , G06F17/16 , G06F17/18 , G06F16/2457
Abstract: Features are provided for the analysis of collections of data and automatic grouping of data having certain similarities. A collection of data regarding user interactions with item-specific content can be analyzed. The analysis can be used to identify groups of items that are of interest to groups of similar users and/or to identify groups of users with demonstrated interests in groups of similar items. Data may be analyzed in a “bottom-up” manner in which correlations within the data are discovered in an iterative manner, or in a “top-down” manner in which desired top-level groups are specified at the beginning of the process. A bottom-up process may also be distributed among multiple devices or processors to more efficiently discover groups when using large collections of data.
-
Patent Agency Ranking
公开(公告)号：US11748610B1
公开(公告)日：2023-09-05
申请号：US15934712
申请日：2018-03-23
Applicant: Amazon Technologies, Inc.
Inventor： Orchid Majumder , Vineet Khare , Leo Parker Dirac , Saurabh Gupta
CPC classification number: G06N3/08 , G06F9/45558 , G06F9/547 , G06N3/044 , G06F2009/45575 , G06F2009/45595
Abstract: Techniques for sequence to sequence (S2S) model building and/or optimization are described. For example, a method of receiving a request to build a sequence to sequence (S2S) model for a use case, wherein the request includes at least a training data set, generating parts of a S2S algorithm based on the at least one use case, determined parameters, and determined hyperparameters, and training a S2S algorithm built from the parts of the S2S algorithm using the training data set to generate the S2S model is detailed.
-
公开(公告)号：US10572321B2
公开(公告)日：2020-02-25
申请号：US15919178
申请日：2018-03-12
Applicant: Amazon Technologies, Inc.
Inventor： Vineet Khare , Alexander Johannes Smola , Craig Wiley
Abstract: Techniques for providing and servicing listed repository items such as algorithms, data, models, pipelines, and/or notebooks are described. In some examples, web services provider receives a request for a listed repository item from a requester, the request indicating at least a category of the repository item and each listing of a repository item includes an indication of a category that the listed repository item belongs to and a storage location of the listed repository item, determines a suggestion of at least one listed repository item based on the request, and provides the suggestion of the at least one listed repository item to the requester.
-
公开(公告)号：US10360482B1
公开(公告)日：2019-07-23
申请号：US15830952
申请日：2017-12-04
Applicant: Amazon Technologies, Inc.
Inventor： Vineet Khare , Gurumurthy Swaminathan , Xiong Zhou
Abstract: Features related to systems and methods for generating a machine learning model that is a composite of at least two other models (e.g., crowd-sourced models contributed by users) are described. Each of the contributed models provide output values that may not be to scale. To account for these differences, a normalization factor for a first machine learning model is generated to adjust values produced by the first machine learning model to correspond with results from the second machine learning model. The crowd-sourced models along with the normalization factor are included in the new image model generated in the claims.
-
公开(公告)号：US11809992B1
公开(公告)日：2023-11-07
申请号：US16836376
申请日：2020-03-31
Applicant: Amazon Technologies, Inc.
Inventor： Gurumurthy Swaminathan , Ragav Venkatesan , Xiong Zhou , Runfei Luo , Vineet Khare
Abstract: Neural networks with similar architectures may be compressed using shared compression profiles. A request to compress a trained neural network may be received and an architecture of the neural network identified. The identified architecture may be compared with the different network architectures mapped to compression profiles to select a compression profile for the neural network. The compression profile may be applied to remove features of the neural network to generate a compressed version of the neural network.
-
公开(公告)号：US11501173B1
公开(公告)日：2022-11-15
申请号：US16831595
申请日：2020-03-26
Applicant: Amazon Technologies, Inc.
Inventor： Gurumurthy Swaminathan , Ragav Venkatesan , Xiong Zhou , Runfei Luo , Vineet Khare
Abstract: A compression policy to produce compression profiles for compressing trained machine learning models may be trained using reinforcement learning. An iterative reinforcement learning may be performed response to a search request. Different prospective compression profiles may be generated for received machine learning models according to a compression policy being trained. Performance of compressed versions of the trained neural networks according to the compression profiles may be caused using data sets used to train the machine learning models. The compression policy may be updated according to reward signal determined from an application of a reward function for performance criteria to performance results of the different versions of the machine learning models. When a search criteria is satisfied, the trained compression policy may be provided.
-
-
-
-
-
-
-
-
-
Search Results
17
records
(took 0.015 seconds)
