公开(公告)号：WO2020237168A1

公开(公告)日：2020-11-26

申请号：PCT/US2020/034267

申请日：2020-05-22

Applicant: GOOGLE LLC

Inventor： RYOO, Michael Sahngwon ,  PIERGIOVANNI, Anthony Jacob ,  TAN, Mingxing ,  ANGELOVA, Anelia

IPC: G06N3/04 ,  G06N3/08

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for determining one or more neural network architectures of a neural network for performing a video processing neural network task. In one aspect, a method comprises: at each of a plurality of iterations: selecting a parent neural network architecture from a set of neural network architectures; training a neural network having the parent neural network architecture to perform the video processing neural network task, comprising determining trained values of connection weight parameters of the parent neural network architecture; generating a new neural network architecture based at least in part on the trained values of the connection weight parameters of the parent neural network architecture; and adding the new neural network architecture to the set of neural network architectures.

公开(公告)号：WO2022015822A1

公开(公告)日：2022-01-20

申请号：PCT/US2021/041583

申请日：2021-07-14

Applicant: GOOGLE LLC

Inventor： RYOO, Michael Sahngwon ,  PIERGIOVANNI, Anthony Jacob ,  ANGELOVA, Anelia

IPC: G06N3/04 ,  G06N3/08

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for processing a network input using a neural network to generate a network output. In one aspect, a method comprises processing a network input using a neural network to generate a network output, where the neural network has multiple blocks, wherein each block is configured to process a block input to generate a block output, the method comprising, for each target block of the neural network: generating attention-weighted representations of multiple first block outputs, comprising, for each first block output: processing multiple second block outputs to generate attention factors; and generating the attention-weighted representation of each first block output by applying the respective attention factors to the corresponding first block output; and generating the target block input from the attention-weighted representations; and processing the target block input using the target block to generate a target block output.

公开(公告)号：WO2021055442A1

公开(公告)日：2021-03-25

申请号：PCT/US2020/051027

申请日：2020-09-16

Applicant: GOOGLE LLC

Inventor： ANGELOVA, Anelia ,  PIERGIOVANNI, Anthony J. ,  RYOO, Michael Sahngwon

IPC: H04N21/44 ,  G06K9/46 ,  G06K9/62 ,  G06N3/04 ,  G06N3/08 ,  H04N19/61 ,  G06N3/063 ,  G06N3/00

Abstract: Generally, the present disclosure is directed to a neural architecture search process for finding small and fast video processing networks for understanding of video data. The neural architecture search process can automatically design networks that provide comparable video processing performance at a fraction of the computational and storage cost of larger existing models, thereby conserving computing resources such as memory and processor usage.