公开(公告)号：US20210232912A1

公开(公告)日：2021-07-29

申请号：US16972429

申请日：2019-09-19

Applicant: Google LLC

Inventor： Abhanshu Sharma ,  Alexander Mordvintsev ,  Matthew Sharifi

IPC: G06N3/08 ,  G06N3/04

Abstract: A computing device is disclosed that includes at least one processor and a machine-learned model. The machine-learned model can include a plurality of blocks and one or more residual connections between two or more of the plurality of blocks. The machine-learned model can be configured to receive a model input and, in response to receipt of the model input, output a model output. The machine-learned model can be configured to perform operations including determining a resource allocation parameter that corresponds to a desired allocation of system resources to the machine-learned model at an inference time; deactivating a subset of the plurality of blocks of the machine-learned model based on the resource allocation parameter; inputting the model input into the machine-learned model with the subset of the plurality of blocks deactivated; and receiving, as an output of the machine-learned model, the model output.

公开(公告)号：US10755171B1

公开(公告)日：2020-08-25

申请号：US15203676

申请日：2016-07-06

Applicant: Google LLC

Inventor： Matthew Sharifi ,  Alexander Mordvintsev

IPC: G06N3/08 ,  G06N20/00

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for hiding information using neural networks. One of the methods includes maintaining data mapping each of a plurality of classes to a respective piece of information that may potentially be hidden in a received data item; receiving a new data item; receiving data identifying a first piece of information to be hidden in the new data item; and modifying the new data item to generate a modified data item that, when processed by a neural network configured to classify input data items belonging to one of the plurality of classes, is classified by the neural network as belonging to a first class of the plurality of classes that is mapped to the first piece of information in the maintained data.

公开(公告)号：US20200057936A1

公开(公告)日：2020-02-20

申请号：US16461287

申请日：2017-11-15

Applicant: GOOGLE LLC

Inventor： Philip Haeusser ,  Alexander Mordvintsev

IPC: G06N3/04 ,  G06N3/08 ,  G06F17/18 ,  G06F17/16 ,  G06K9/62

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a neural network. One of the methods includes obtaining a batch of labeled training items and a batch of unlabeled training items; processing the labeled training items and the unlabeled training items using the neural network and in accordance with current values of the network parameters to generate respective embeddings; determining a plurality of similarity values, each similarity value measuring a similarity between the embedding for a respective labeled training item and the embedding for a respective unlabeled training item; determining a respective roundtrip path probability for each of a plurality of roundtrip paths; and performing an iteration of a neural network training procedure to determine a first value update to the current values of the network parameters that decreases roundtrip path probabilities for incorrect roundtrip paths.

公开(公告)号：US20190228587A1

公开(公告)日：2019-07-25

申请号：US15878621

申请日：2018-01-24

Applicant: Google LLC

Inventor： Alexander Mordvintsev ,  Matthew Sharifi

IPC: G06T19/20 ,  G06T15/04 ,  G06T15/20 ,  G06K9/62

Abstract: Example aspects of the present disclosure are directed to systems and methods that perform image style transfer for three-dimensional models. In some implementations, the systems and methods can use machine-learned models such as, for example, convolutional neural networks to generate image style and content information used to perform style transfer. The systems and methods of the present disclosure can operate in a rendered image space. In particular, a computing system can iteratively modify an attribute rendering map (e.g., texture map, bump map, etc.) based on information collected from a different rendering of the model at each of a plurality of iterations, with the end result being that the attribute rendering map mimics the style of one or more reference images in content-preserving way. In some implementations, a computation of style loss at each iteration can be performed using multi-viewpoint averaged scene statistics, instead of treating each viewpoint independently.

公开(公告)号：US11443170B2

公开(公告)日：2022-09-13

申请号：US16461287

申请日：2017-11-15

Applicant: GOOGLE LLC

Inventor： Philip Haeusser ,  Alexander Mordvintsev

IPC: G06N3/04 ,  G06F17/16 ,  G06F17/18 ,  G06K9/62 ,  G06N3/08

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a neural network. One of the methods includes obtaining a batch of labeled training items and a batch of unlabeled training items; processing the labeled training items and the unlabeled training items using the neural network and in accordance with current values of the network parameters to generate respective embeddings; determining a plurality of similarity values, each similarity value measuring a similarity between the embedding for a respective labeled training item and the embedding for a respective unlabeled training item; determining a respective roundtrip path probability for each of a plurality of roundtrip paths; and performing an iteration of a neural network training procedure to determine a first value update to the current values of the network parameters that decreases roundtrip path probabilities for incorrect roundtrip paths.

公开(公告)号：US20210383221A1

公开(公告)日：2021-12-09

申请号：US17337790

申请日：2021-06-03

Applicant: Google LLC

Inventor： Ettore Randazzo ,  Eyvind Niklasson ,  Alexander Mordvintsev

IPC: G06N3/08 ,  G06N3/04

Abstract: Systems and methods are directed to a computing system. The computing system can include one or more processors and a machine-learned message passing model that is end-to-end differentiable. The machine-learned message passing model can include a plurality of nodes. That each include a machine-learned backmessage generation submodel. Each of the one or more nodes can be configured to receive at least one backmessage from at least one downstream node, generate, using the machine-learned backmessage generation submodel, a multi-dimensional backmessage based on the at least one backmessage, and provide the multi-dimensional backmessage to at least one upstream node. The computing system can, for one or more iterations, update, for each of the one or more nodes, one or more parameters of the machine-learned backmessage generation submodel of the node based on a meta-learning objective function.

公开(公告)号：US10467820B2

公开(公告)日：2019-11-05

申请号：US15878621

申请日：2018-01-24

Applicant: Google LLC

Inventor： Alexander Mordvintsev ,  Matthew Sharifi

IPC: G06T19/20 ,  G06T15/04 ,  G06K9/62 ,  G06T15/20

Abstract: Example aspects of the present disclosure are directed to systems and methods that perform image style transfer for three-dimensional models. In some implementations, the systems and methods can use machine-learned models such as, for example, convolutional neural networks to generate image style and content information used to perform style transfer. The systems and methods of the present disclosure can operate in a rendered image space. In particular, a computing system can iteratively modify an attribute rendering map (e.g., texture map, bump map, etc.) based on information collected from a different rendering of the model at each of a plurality of iterations, with the end result being that the attribute rendering map mimics the style of one or more reference images in content-preserving way. In some implementations, a computation of style loss at each iteration can be performed using multi-viewpoint averaged scene statistics, instead of treating each viewpoint independently.