公开(公告)号：US20240386529A1

公开(公告)日：2024-11-21

申请号：US18667132

申请日：2024-05-17

Applicant: Google LLC

Inventor： Mengjiao Yang ,  Yilun Du ,  Bo Dai ,  Dale Eric Schuurmans

IPC: G06T5/60 ,  G06T5/70 ,  G06T13/00

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating an output video conditioned on an input. The video generation method can be implemented by a system including one or more computers. The system receives a conditioning input, and initializes a current intermediate representation of the output video. At each of a plurality of iterations, the system updates the current intermediate representation using a first denoising diffusion model and a second denoising diffusion model conditioned on the conditioning input.

公开(公告)号：US20240112013A1

公开(公告)日：2024-04-04

申请号：US17951889

申请日：2022-09-23

Applicant: Google LLC

Inventor： Hanjun Dai ,  Bo Dai ,  Mengjiao Yang ,  Yuan Xue ,  Dale Eric Schuurmans

IPC: G06N3/08 ,  G06N3/04

CPC classification number: G06N3/08 ,  G06N3/0472

Abstract: The present disclosure is directed to generative models for datasets constrained by marginal constraints. One method includes receiving a request to generate a target dataset based on a marginal constraint for a source dataset. A first object occurs at a source frequency in the source dataset. The marginal constraint indicates a target frequency for the first object. The source dataset encodes a set of co-occurrence frequencies for a plurality of object pairs. A source generative model is accessed. The source generative model includes a first module and a second module that are trained on the source dataset. The second module is updated based on the marginal constraint. An adapted generative model is generated that includes the first module and the updated second module. The target dataset is generated based on the adapted generative model. The first object occurs at the target frequency in the target dataset. The target dataset encodes the set of co-occurrence frequencies for the plurality of object pairs.

公开(公告)号：US20230022151A1

公开(公告)日：2023-01-26

申请号：US17860691

申请日：2022-07-08

Applicant: Google LLC

Inventor： Hanjun Dai ,  Bo Dai ,  Hongyu Ren ,  Dale Eric Schuurmans ,  Zihang Dai ,  Mengjiao Yang

IPC: G06F40/20 ,  G06N20/00

Abstract: The present disclosure is directed to machine learning model architectures which provide full attention capability in each attention head while maintaining low computation and memory complexity. Specifically, according to one aspect of the present disclosure, example attention models provided herein can treat the self-attention mechanism as a conditional expectation over embeddings at each location and approximate the conditional distribution with a structured factorization. Each location can attend to all other locations, either via direct attention, or through indirect attention to group representations, which are again conditional expectations of embeddings from corresponding local regions.

公开(公告)号：US20220343152A1

公开(公告)日：2022-10-27

申请号：US17239320

申请日：2021-04-23

Applicant: Google LLC

Inventor： Bo Dai ,  Mengjiao Yang ,  Hanjun Dai ,  Dale Eric Schuurmans

IPC: G06N3/08 ,  G06N3/04

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generative modelling of an exchangeable sets. Methods can include obtaining a dataset of training observations. Each training observation is an exchangeable set that includes a plurality of data points. Each training observations is processed using a first neural network to generate parameters of a first probability distribution based on which a latent variable is sampled. The latent variable is processed using a second neural network to generate a new observation that includes a plurality of data points. The training observation and the new observation is processed using an energy neural network to generate an estimate of an energy of the training observation and the new observation. The energy neural network is then trained to optimize an objective function that measures the difference between the estimate of the energy of the training observation and the new observation.