公开(公告)号：US11533495B2

公开(公告)日：2022-12-20

申请号：US17162150

申请日：2021-01-29

Applicant: Google LLC

Inventor： Vihan Jain ,  Joonseok Lee ,  Ming Zhao ,  Sheide Chammas ,  Hexiang Hu ,  Bowen Zhang ,  Fei Sha ,  Tze Way Eugene Ie

IPC: H04N19/30 ,  H04N19/00 ,  H04N19/172 ,  G06N20/00

Abstract: A computer-implemented method for generating video representations utilizing a hierarchical video encoder includes obtaining a video, wherein the video includes a plurality of frames, processing each of the plurality of frames with a machine-learned frame-level encoder model to respectively generate a plurality of frame representations for the plurality of frames, the plurality of frame representations respective to the plurality of frames determining a plurality of segment representations representative of a plurality of video segments including one or more of the plurality of frames, the plurality of segment representations based at least in part on the plurality of frame representations, processing the plurality of segment representations with a machine-learned segment-level encoder model to generate a plurality of contextualized segment representations, determining a video representation based at least in part on the plurality of contextualized segment representations, and providing the video representation as an output.

公开(公告)号：US10062035B1

公开(公告)日：2018-08-28

申请号：US14104004

申请日：2013-12-12

Applicant: Google LLC

Inventor： Tal Shaked ,  Tushar Deepak Chandra ,  Yoram Singer ,  Tze Way Eugene Ie ,  Joshua Redstone

IPC: G06F15/18 ,  G06N99/00 ,  G06F12/02

CPC classification number: G06N20/00

Abstract: The present disclosure provides methods and systems for using variable length representations of machine learning statistics. A method may include storing an n-bit representation of a first statistic at a first n-bit storage cell. A first update to the first statistic may be received, and it may be determined that the first update causes a first loss of precision of the first statistic as stored in the first n-bit storage cell. Accordingly, an m-bit representation of the first statistic may be stored at a first m-bit storage cell based on the determination. The first m-bit storage cell may be associated with the first n-bit storage cell. As a result, upon receiving an instruction to use the first statistic in a calculation, a combination of the n-bit representation and the m-bit representation may be used to perform the calculation.

公开(公告)号：US10713585B2

公开(公告)日：2020-07-14

申请号：US14106900

申请日：2013-12-16

Applicant: Google LLC

Inventor： Tal Shaked ,  Tushar Deepak Chandra ,  James Vincent McFadden ,  Yoram Singer ,  Tze Way Eugene Ie

IPC: G06N20/00

Abstract: Systems and techniques are provided for template exploration in a large-scale machine learning system. A method may include obtaining multiple base templates, each base template comprising multiple features. A template performance score may be obtained for each base template and a first base template may be selected from among the multiple base templates based on the template performance score of the first base template. Multiple cross-templates may be constructed by generating a cross-template of the selected first base template and each of the multiple base templates. Performance of a machine learning model may be tested based on each cross-template to generate a cross-template performance score for each of the cross-templates. A first cross-template may be selected from among the multiple cross-templates based on the cross-template performance score of the cross-template. Accordingly, the first cross-template may be added to the machine learning model.