公开(公告)号：US20240054043A1

公开(公告)日：2024-02-15

申请号：US18359288

申请日：2023-07-26

申请人： NEC Laboratories America, Inc.

发明人： Zhengzhang Chen ,  Haifeng Chen ,  Liang Tong ,  Dongjie Wang

IPC分类号： G06F11/07

CPC分类号： G06F11/079 ,  G06F11/0709 ,  G06F11/076

摘要： A computer-implemented method for detecting trigger points to identify root cause failure and fault events is provided. The method includes collecting, by a monitoring agent, entity metrics data and system key performance indicator (KPI) data, integrating the entity metrics data and the KPI data, constructing an initial system state space, detecting system state changes by calculating a distance between current batch data and an initial state, and dividing a system status into different states.

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：US20220067521A1

公开(公告)日：2022-03-03

申请号：US17464148

申请日：2021-09-01

申请人： NEC Laboratories America, Inc.

发明人： Zhengzhang Chen ,  Haifeng Chen ,  Liang Tong

IPC分类号： G06N3/08 ,  G06K9/00 ,  G06K9/20 ,  G06K9/62

摘要： Methods and systems for enhancing a neural network include detecting an occlusion in an input image using a trained occlusion detection neural network. The detected occlusion is replaced in the input image with a neutral occlusion to prevent the detected occlusion from frustrating facial recognition to generate a modified input image. Facial recognition is performed on the modified input image using a trained facial recognition neural network.

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：US12008471B2

公开(公告)日：2024-06-11

申请号：US17464127

申请日：2021-09-01

申请人： NEC Laboratories America, Inc.

发明人： Zhengzhang Chen ,  Haifeng Chen ,  Liang Tong

IPC分类号： G06N3/08 ,  G06F18/21 ,  G06F18/28 ,  G06V10/22 ,  G06V40/16

CPC分类号： G06N3/08 ,  G06F18/2163 ,  G06F18/28 ,  G06V10/22 ,  G06V40/171 ,  G06V40/172

摘要： Methods and systems for evaluating and enhancing a neural network model include constructing a surrogate model that corresponds to a target neural network model, based on a degree of knowledge about the target neural network model. Adversarial attacks against the surrogate model are generated, based on an attack goal, a level of attacker capability, and an attack model. The target neural network model is tested for accuracy under the generated adversarial attacks to determine a degree of robustness of the target neural network. Robustness of the target neural network model is enhanced by replacing facial occlusions in input images before applying the input images to the target neural network.

公开(公告)号：US20230130188A1

公开(公告)日：2023-04-27

申请号：US17969349

申请日：2022-10-19

申请人： NEC Laboratories America, Inc.

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

IPC分类号： G06N3/08

摘要： Methods and systems for training a model include collecting unlabeled training data during operation of a device. A model is adapted to operational conditions of the device using the unlabeled training data. The model includes a shared encoder that is trained on labeled training data from multiple devices and further includes a device-specific decoder that is trained on labeled training data corresponding to the device.

公开(公告)号：US20220067432A1

公开(公告)日：2022-03-03

申请号：US17464127

申请日：2021-09-01

申请人： NEC Laboratories America, Inc.

发明人： Zhengzhang Chen ,  Haifeng Chen ,  Liang Tong

IPC分类号： G06K9/62

摘要： Methods and systems for evaluating and enhancing a neural network model include constructing a surrogate model that corresponds to a target neural network model, based on a degree of knowledge about the target neural network model. Adversarial attacks against the surrogate model are generated, based on an attack goal, a level of attacker capability, and an attack model. The target neural network model is tested for accuracy under the generated adversarial attacks to determine a degree of robustness of the target neural network. Robustness of the target neural network model is enhanced by replacing facial occlusions in input images before applying the input images to the target neural network.

公开(公告)号：US20240070232A1

公开(公告)日：2024-02-29

申请号：US18452664

申请日：2023-08-21

申请人： NEC Laboratories America, Inc.

发明人： Wei Cheng ,  Jingchao Ni ,  Liang Tong ,  Haifeng Chen ,  Yizhou Zhang

IPC分类号： G06F18/2413 ,  G06F18/2415 ,  H04B10/69

CPC分类号： G06F18/24133 ,  G06F18/2415 ,  H04B10/697

摘要： Methods and systems for training a model include determining class prototypes of time series samples from a training dataset. A task corresponding to the time series samples is encoded using the class prototypes and a task-level configuration. A likelihood value is determined based on outputs of a time series density model, a task-class distance from a task embedding model, and a task density model. Parameters of the time series density model, the task embedding model, and the task density model are adjusted responsive to the likelihood value.

公开(公告)号：US20240062043A1

公开(公告)日：2024-02-22

申请号：US18364746

申请日：2023-08-03

申请人： NEC Laboratories America, Inc.

发明人： Liang Tong ,  Zhengzhang Chen ,  Wei Cheng ,  Haifeng Chen ,  Zhuohang Li

IPC分类号： G06N3/0455 ,  G06N3/08

CPC分类号： G06N3/0455 ,  G06N3/08

摘要： A computer-implemented method for employing a graph-based adaptive domain generation framework is provided. The method includes, in a training phase, performing domain prototypical network training on source domains, constructing an autoencoding domain relation graph by applying a graph autoencoder to produce domain node embeddings, and performing, via a domain-adaptive classifier, domain-adaptive classifier training to make an informed decision. The method further includes, in a testing phase, given testing samples from a new source domain, computing a prototype by using a pretrained domain prototypical network, inferring node embedding, and making a prediction by the domain-adaptive classifier based on the domain node embeddings.

公开(公告)号：US20240061740A1

公开(公告)日：2024-02-22

申请号：US18359350

申请日：2023-07-26

申请人： NEC Laboratories America, Inc.

发明人： Zhengzhang Chen ,  Haifeng Chen ,  Liang Tong ,  Dongjie Wang

IPC分类号： G06F11/07 ,  G06F11/34

CPC分类号： G06F11/079 ,  G06F11/3447

摘要： A computer-implemented method for locating root causes is provided. The method includes detecting a trigger point from entity metrics data and key performance indicator (KPI) data, generating a learned causal graph by fusing a state-invariant causal graph with a state-dependent causal graph, and locating the root causes by employing a random walk-based technique to estimate a probability score for each of the entity metrics data by starting from a KPI node.