公开(公告)号：US20230252302A1

公开(公告)日：2023-08-10

申请号：US18152238

申请日：2023-01-10

申请人： NEC Laboratories America, Inc.

发明人： Liang Tong ,  Takehiko Mizoguchi ,  Zhengzhang Chen ,  Wei Cheng ,  Haifeng Chen ,  Nauman Ahad

IPC分类号： G06N3/0895 ,  G06N3/0442

CPC分类号： G06N3/0895 ,  G06N3/0442

摘要： A computer-implemented method for ordinal prediction is provided. The method includes encoding time series data with a temporal encoder to obtain latent space representations. The method includes optimizing the temporal encoder using semi-supervised learning to distinguish different classes in the labeled space using labeled data, and augment the latent space representations using unlabeled training data, to obtain semi-supervised representations. The method further includes discarding a linear layer after the temporal encoder and fixing the temporal encoder. The method also includes training k−1 binary classifiers on top of the semi-supervised representations to obtain k−1 binary predictions. The method additionally includes identifying and correcting inconsistent ones of the k−1 binary predictions by matching the inconsistent ones to consistent ones of the k−1 binary predictions. The method further includes aggregating the k−1 binary predictions to obtain an ordinal prediction.

公开(公告)号：US20240232638A1

公开(公告)日：2024-07-11

申请号：US18545042

申请日：2023-12-19

申请人： NEC Laboratories America, Inc.

发明人： Liang Tong ,  Takehiko Mizoguchi ,  Zhengzhang Chen ,  Wei Cheng ,  Haifeng Chen ,  Nauman Ahad

IPC分类号： G06N3/0895 ,  G06N3/0442

CPC分类号： G06N3/0895 ,  G06N3/0442

摘要： A computer-implemented method for ordinal prediction is provided. The method includes encoding time series data with a temporal encoder to obtain latent space representations. The method includes optimizing the temporal encoder using semi-supervised learning to distinguish different classes in the labeled space using labeled data, and augment the latent space representations using unlabeled training data, to obtain semi-supervised representations. The method further includes discarding a linear layer after the temporal encoder and fixing the temporal encoder. The method also includes training k-1 binary classifiers on top of the semi-supervised representations to obtain k-1 binary predictions. The method additionally includes identifying and correcting inconsistent ones of the k-1 binary predictions by matching the inconsistent ones to consistent ones of the k-1 binary predictions. The method further includes aggregating the k-1 binary predictions to obtain an ordinal prediction.

公开(公告)号：US20240135188A1

公开(公告)日：2024-04-25

申请号：US18545055

申请日：2023-12-19

申请人： NEC Laboratories America, Inc.

发明人： Liang Tong ,  Takehiko Mizoguchi ,  Zhengzhang Chen ,  Wei Cheng ,  Haifeng Chen ,  Nauman Ahad

IPC分类号： G06N3/0895 ,  G06N3/0442

CPC分类号： G06N3/0895 ,  G06N3/0442

摘要： A computer-implemented method for ordinal prediction is provided. The method includes encoding time series data with a temporal encoder to obtain latent space representations. The method includes optimizing the temporal encoder using semi-supervised learning to distinguish different classes in the labeled space using labeled data, and augment the latent space representations using unlabeled training data, to obtain semi-supervised representations. The method further includes discarding a linear layer after the temporal encoder and fixing the temporal encoder. The method also includes training k-1 binary classifiers on top of the semi-supervised representations to obtain k-1 binary predictions. The method additionally includes identifying and correcting inconsistent ones of the k-1 binary predictions by matching the inconsistent ones to consistent ones of the k-1 binary predictions. The method further includes aggregating the k-1 binary predictions to obtain an ordinal prediction.

公开(公告)号：US20240127072A1

公开(公告)日：2024-04-18

申请号：US18545025

申请日：2023-12-19

申请人： NEC Laboratories America, Inc.

发明人： Liang Tong ,  Takehiko Mizoguchi ,  Zhengzhang Chen ,  Wei Cheng ,  Haifeng Chen ,  Nauman Ahad

IPC分类号： G06N3/0895 ,  G06N3/0442

CPC分类号： G06N3/0895 ,  G06N3/0442

摘要： A computer-implemented method for ordinal prediction is provided. The method includes encoding time series data with a temporal encoder to obtain latent space representations. The method includes optimizing the temporal encoder using semi-supervised learning to distinguish different classes in the labeled space using labeled data, and augment the latent space representations using unlabeled training data, to obtain semi-supervised representations. The method further includes discarding a linear layer after the temporal encoder and fixing the temporal encoder. The method also includes training k−1 binary classifiers on top of the semi-supervised representations to obtain k−1 binary predictions. The method additionally includes identifying and correcting inconsistent ones of the k−1 binary predictions by matching the inconsistent ones to consistent ones of the k−1 binary predictions. The method further includes aggregating the k−1 binary predictions to obtain an ordinal prediction.