中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

11 records (took 0.016 seconds)

    Systems and methods for collaborative filtering with variational autoencoders
    5.
    发明授权
    Systems and methods for collaborative filtering with variational autoencoders 有权

    公开(公告)号：US11586915B2

    公开(公告)日：2023-02-21

    申请号：US16772094

    申请日：2018-12-12

    Applicant: D-WAVE SYSTEMS INC.

    Inventor： William G. Macready ,  Jason T. Rolfe

    IPC: G06N3/08 ,  G06N10/00 ,  G06K9/62 ,  G06N3/04

    Abstract: Collaborative filtering systems based on variational autoencoders (VAEs) are provided. VAEs may be trained on row-wise data without necessarily training a paired VAE on column-wise data (or vice-versa), and may optionally be trained via minibatches. The row-wise VAE models the output of the corresponding column-based VAE as a set of parameters and uses these parameters in decoding. In some implementations, a paired VAE is provided which receives column-wise data and models row-wise parameters; each of the paired VAEs may bind their learned column- or row-wise parameters to the output of the corresponding VAE. The paired VAEs may optionally be trained via minibatches. Unobserved data may be explicitly modelled. Methods for performing inference with such VAE-based collaborative filtering systems are also disclosed, as are example applications to search and anomaly detection.

    Systems and methods for collaborative filtering with variational autoencoders
    8.
    发明授权
    Systems and methods for collaborative filtering with variational autoencoders 有权

    公开(公告)号：US12198051B2

    公开(公告)日：2025-01-14

    申请号：US18096198

    申请日：2023-01-12

    Applicant: D-WAVE SYSTEMS INC.

    Inventor： William G. Macready ,  Jason T. Rolfe

    IPC: G06N3/047 ,  G06F18/214 ,  G06N3/045 ,  G06N3/08 ,  G06N10/00

    Abstract: Collaborative filtering systems based on variational autoencoders (VAEs) are provided. VAEs may be trained on row-wise data without necessarily training a paired VAE on column-wise data (or vice-versa), and may optionally be trained via minibatches. The row-wise VAE models the output of the corresponding column-based VAE as a set of parameters and uses these parameters in decoding. In some implementations, a paired VAE is provided which receives column-wise data and models row-wise parameters; each of the paired VAEs may bind their learned column- or row-wise parameters to the output of the corresponding VAE. The paired VAEs may optionally be trained via minibatches. Unobserved data may be explicitly modelled. Methods for performing inference with such VAE-based collaborative filtering systems are also disclosed, as are example applications to search and anomaly detection.

    SYSTEMS AND METHODS FOR COLLABORATIVE FILTERING WITH VARIATIONAL AUTOENCODERS
    9.
    发明公开
    SYSTEMS AND METHODS FOR COLLABORATIVE FILTERING WITH VARIATIONAL AUTOENCODERS 审中-公开

    公开(公告)号：US20230222337A1

    公开(公告)日：2023-07-13

    申请号：US18096198

    申请日：2023-01-12

    Applicant: D-WAVE SYSTEMS INC.

    Inventor： William G. Macready ,  Jason T. Rolfe

    IPC: G06N3/08 ,  G06N10/00

    CPC classification number: G06N3/08 ,  G06N10/00 ,  G06N3/045 ,  G06F18/2148

    Abstract: Collaborative filtering systems based on variational autoencoders (VAEs) are provided. VAEs may be trained on row-wise data without necessarily training a paired VAE on column-wise data (or vice-versa), and may optionally be trained via minibatches. The row-wise VAE models the output of the corresponding column-based VAE as a set of parameters and uses these parameters in decoding. In some implementations, a paired VAE is provided which receives column-wise data and models row-wise parameters; each of the paired VAEs may bind their learned column- or row-wise parameters to the output of the corresponding VAE. The paired VAEs may optionally be trained via minibatches. Unobserved data may be explicitly modelled. Methods for performing inference with such VAE-based collaborative filtering systems are also disclosed, as are example applications to search and anomaly detection.

    SYSTEMS AND METHODS FOR COLLABORATIVE FILTERING WITH VARIATIONAL AUTOENCODERS
    10.
    发明申请
    SYSTEMS AND METHODS FOR COLLABORATIVE FILTERING WITH VARIATIONAL AUTOENCODERS 有权

    公开(公告)号：US20210089884A1

    公开(公告)日：2021-03-25

    申请号：US16772094

    申请日：2018-12-12

    Applicant: D-WAVE SYSTEMS INC.

    Inventor： William G. Macready ,  Jason T. Rolfe

    IPC: G06N3/08 ,  G06N3/04 ,  G06N10/00 ,  G06K9/62

    Abstract: Collaborative filtering systems based on variational autoencoders (VAEs) are provided. VAEs may be trained on row-wise data without necessarily training a paired VAE on column-wise data (or vice-versa), and may optionally be trained via minibatches. The row-wise VAE models the output of the corresponding column-based VAE as a set of parameters and uses these parameters in decoding. In some implementations, a paired VAE is provided which receives column-wise data and models row-wise parameters; each of the paired VAEs may bind their learned column- or row-wise parameters to the output of the corresponding VAE. The paired VAEs may optionally be trained via minibatches. Unobserved data may be explicitly modelled. Methods for performing inference with such VAE-based collaborative filtering systems are also disclosed, as are example applications to search and anomaly detection.

Patent Agency Ranking