-
公开(公告)号：US10417562B2
公开(公告)日：2019-09-17
申请号：US15009647
申请日：2016-01-28
Applicant: Google LLC
Inventor： Sergey Ioffe , Corinna Cortes
Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing inputs using a neural network system that includes a batch normalization layer. One of the methods includes receiving a respective first layer output for each training example in the batch; computing a plurality of normalization statistics for the batch from the first layer outputs; normalizing each component of each first layer output using the normalization statistics to generate a respective normalized layer output for each training example in the batch; generating a respective batch normalization layer output for each of the training examples from the normalized layer outputs; and providing the batch normalization layer output as an input to the second neural network layer.
-
公开(公告)号：US11934956B2
公开(公告)日：2024-03-19
申请号：US18071806
申请日：2022-11-30
Applicant: Google LLC
Inventor： Sergey Ioffe
IPC: G06N3/08 , G06F18/214 , G06F18/2413 , G06N3/04 , G06V10/44 , G06V10/764 , G06V10/774
CPC classification number: G06N3/08 , G06F18/214 , G06F18/24137 , G06N3/04 , G06V10/454 , G06V10/764 , G06V10/774
Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage medium, for training a neural network, wherein the neural network is configured to receive an input data item and to process the input data item to generate a respective score for each label in a predetermined set of multiple labels. The method includes actions of obtaining a set of training data that includes a plurality of training items, wherein each training item is associated with a respective label from the predetermined set of multiple labels; and modifying the training data to generate regularizing training data, comprising: for each training item, determining whether to modify the label associated with the training item, and changing the label associated with the training item to a different label from the predetermined set of labels, and training the neural network on the regularizing data.
-
公开(公告)号：US11531874B2
公开(公告)日：2022-12-20
申请号：US15343458
申请日：2016-11-04
Applicant: Google LLC
Inventor： Sergey Ioffe
Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage medium, for training a neural network, wherein the neural network is configured to receive an input data item and to process the input data item to generate a respective score for each label in a predetermined set of multiple labels. The method includes actions of obtaining a set of training data that includes a plurality of training items, wherein each training item is associated with a respective label from the predetermined set of multiple labels; and modifying the training data to generate regularizing training data, comprising: for each training item, determining whether to modify the label associated with the training item, and changing the label associated with the training item to a different label from the predetermined set of labels, and training the neural network on the regularizing data.
-
公开(公告)号：US20210224653A1
公开(公告)日：2021-07-22
申请号：US17156453
申请日：2021-01-22
Applicant: Google LLC
Inventor： Sergey Ioffe , Corinna Cortes
Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing inputs using a neural network system that includes a batch normalization layer. One of the methods includes receiving a respective first layer output for each training example in the batch; computing a plurality of normalization statistics for the batch from the first layer outputs; normalizing each component of each first layer output using the normalization statistics to generate a respective normalized layer output for each training example in the batch; generating a respective batch normalization layer output for each of the training examples from the normalized layer outputs; and providing the batch normalization layer output as an input to the second neural network layer.
-
公开(公告)号：US20200250543A1
公开(公告)日：2020-08-06
申请号：US16854352
申请日：2020-04-21
Applicant: Google LLC
Inventor： Sergey Ioffe
Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for implementing a neural network. In one aspect, the neural network includes a batch renormalization layer between a first neural network layer and a second neural network layer. The first neural network layer generates first layer outputs having multiple components. The batch renormalization layer is configured to, during training of the neural network on a current batch of training examples, obtain respective current moving normalization statistics for each of the multiple components and determine respective affine transform parameters for each of the multiple components from the current moving normalization statistics. The batch renormalization layer receives a respective first layer output for each training example in the current batch and applies the affine transform to each component of a normalized layer output to generate a renormalized layer output for the training example.
-
Patent Agency Ranking
公开(公告)号：US20200012942A1
公开(公告)日：2020-01-09
申请号：US16572454
申请日：2019-09-16
Applicant: Google LLC
Inventor： Sergey Ioffe , Corinna Cortes
Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing inputs using a neural network system that includes a batch normalization layer. One of the methods includes receiving a respective first layer output for each training example in the batch; computing a plurality of normalization statistics for the batch from the first layer outputs; normalizing each component of each first layer output using the normalization statistics to generate a respective normalized layer output for each training example in the batch; generating a respective batch normalization layer output for each of the training examples from the normalized layer outputs; and providing the batch normalization layer output as an input to the second neural network layer.
-
公开(公告)号：US20190205654A1
公开(公告)日：2019-07-04
申请号：US16298327
申请日：2019-03-11
Applicant: Google LLC
Inventor： Matthias Grundmann , Alexandra Ivanna Hawkins , Sergey Ioffe
CPC classification number: G06K9/00765 , G06K9/00751 , G06K9/623
Abstract: Methods, systems, and media for summarizing a video with video thumbnails are provided. In some embodiments, the method comprises: receiving a plurality of video frames corresponding to the video and associated information associated with each of the plurality of video frames; extracting, for each of the plurality of video frames, a plurality of features; generating candidate clips that each includes at least a portion of the received video frames based on the extracted plurality of features and the associated information; calculating, for each candidate clip, a clip score based on the extracted plurality of features from the video frames associated with the candidate clip; calculating, between adjacent candidate clips, a transition score based at least in part on a comparison of video frame features between frames from the adjacent candidate clips; selecting a subset of the candidate clips based at least in part on the clip score and the transition score associated with each of the candidate clips; and automatically generating an animated video thumbnail corresponding to the video that includes a plurality of video frames selected from each of the subset of candidate clips.
-
公开(公告)号：US10158893B2
公开(公告)日：2018-12-18
申请号：US15928331
申请日：2018-03-22
Applicant: GOOGLE LLC
Inventor： Sergey Ioffe
IPC: H04N7/167 , H04N21/2343 , H04N21/234 , H04N21/233 , H04N21/2743 , H04N21/8355 , H04N21/845
Abstract: A method includes dividing a video uploaded to a user's client device into scenes that include one or more frames. The method also includes generating a digital summary for each scene based on content associated with a respective portion of the video spanned by the scene. The method also includes identifying a matching portion of the uploaded video containing third-party content base on a match between the digital summary associated with the matching portion and the digital summary associated with the third-party content. The method also includes identifying an original portion of the video containing the original content and a usage policy associated with a content owner of the third-party content. The method also includes generating a degraded video based on the usage policy, by applying a quality reduction to the matching portion.
-
公开(公告)号：US12125257B2
公开(公告)日：2024-10-22
申请号：US17372090
申请日：2021-07-09
Applicant: Google LLC
Inventor： Vincent O. Vanhoucke , Christian Szegedy , Sergey Ioffe
IPC: G06K9/62 , G06F18/24 , G06K9/00 , G06K9/46 , G06N3/04 , G06N3/044 , G06N3/08 , G06V10/44 , G06V10/94
Abstract: A neural network system that includes: multiple subnetworks that includes: a first subnetwork including multiple first modules, each first module including: a pass-through convolutional layer configured to process the subnetwork input for the first subnetwork to generate a pass-through output; an average pooling stack of neural network layers that collectively processes the subnetwork input for the first subnetwork to generate an average pooling output; a first stack of convolutional neural network layers configured to collectively process the subnetwork input for the first subnetwork to generate a first stack output; a second stack of convolutional neural network layers that are configured to collectively process the subnetwork input for the first subnetwork to generate a second stack output; and a concatenation layer configured to concatenate the pass-through output, the average pooling output, the first stack output, and the second stack output to generate a first module output for the first module.
-
公开(公告)号：US20240265253A1
公开(公告)日：2024-08-08
申请号：US18582445
申请日：2024-02-20
Applicant: Google LLC
Inventor： Sergey Ioffe
IPC: G06N3/08 , G06F18/214 , G06F18/2413 , G06N3/04 , G06V10/44 , G06V10/764 , G06V10/774
CPC classification number: G06N3/08 , G06F18/214 , G06F18/24137 , G06N3/04 , G06V10/454 , G06V10/764 , G06V10/774
Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage medium, for training a neural network, wherein the neural network is configured to receive an input data item and to process the input data item to generate a respective score for each label in a predetermined set of multiple labels. The method includes actions of obtaining a set of training data that includes a plurality of training items, wherein each training item is associated with a respective label from the predetermined set of multiple labels; and modifying the training data to generate regularizing training data, comprising: for each training item, determining whether to modify the label associated with the training item, and changing the label associated with the training item to a different label from the predetermined set of labels, and training the neural network on the regularizing data.
-
-
-
-
-
-
-
-
-
Search Results
41
records
(took 0.02 seconds)
