公开(公告)号：US20240046092A1

公开(公告)日：2024-02-08

申请号：US18484816

申请日：2023-10-11

Applicant: NEC Laboratories America, Inc.

Inventor： Wenchao Yu ,  Wei Cheng ,  Haifeng Chen ,  Yiwei Sun

IPC: G06N3/08 ,  G06N20/00

CPC classification number: G06N3/08 ,  G06N20/00

Abstract: A method for acquiring skills through imitation learning by employing a meta imitation learning framework with structured skill discovery (MILD) is presented. The method includes learning behaviors or tasks, by an agent, from demonstrations: by learning to decompose the demonstrations into segments, via a segmentation component, the segments corresponding to skills that are transferrable across different tasks, learning relationships between the skills that are transferrable across the different tasks, employing, via a graph generator, a graph neural network for learning implicit structures of the skills from the demonstrations to define structured skills, and generating policies from the structured skills to allow the agent to acquire the structured skills for application to one or more target tasks.

公开(公告)号：US20230401851A1

公开(公告)日：2023-12-14

申请号：US18332057

申请日：2023-06-09

Applicant: NEC Laboratories America, Inc.

Inventor： Xuchao Zhang ,  Xujiang Zhao ,  Yuncong Chen ,  Wenchao Yu ,  Haifeng Chen ,  Wei Cheng

IPC: G06V20/40 ,  G06V20/52 ,  G06V10/82

CPC classification number: G06V20/44 ,  G06V20/52 ,  G06V10/82 ,  G06T2207/20081

Abstract: Methods and systems for event detection include training a joint neural network model with respective neural networks for audio data and video data relating to a same scene. The joint neural network model is configured to output a belief value, a disbelief value, and an uncertainty value. It is determined that an event has occurred based on the belief value, the disbelief value, and the uncertainty value.

公开(公告)号：US20230109729A1

公开(公告)日：2023-04-13

申请号：US17958597

申请日：2022-10-03

Applicant: NEC Laboratories America, Inc.

Inventor： Yuncong Chen ,  Zhengzhang Chen ,  Xuchao Zhang ,  Wenchao Yu ,  Haifeng Chen ,  LuAn Tang ,  Zexue He

IPC: G06N3/08 ,  G06F40/47 ,  G06F40/30

Abstract: A computer-implemented method for multi-model representation learning is provided. The method includes encoding, by a trained time series (TS) encoder, an input TS segment into a TS-shared latent representation and a TS-private latent representation. The method further includes generating, by a trained text generator, a natural language text that explains the input TS segment, responsive to the TS-shared latent representation, the TS-private latent representation, and a text-private latent representation.

公开(公告)号：US11604969B2

公开(公告)日：2023-03-14

申请号：US16553465

申请日：2019-08-28

Applicant: NEC Laboratories America, Inc.

Inventor： Wei Cheng ,  LuAn Tang ,  Dongjin Song ,  Bo Zong ,  Haifeng Chen ,  Jingchao Ni ,  Wenchao Yu

IPC: G06N3/08 ,  G06N5/02 ,  G06N3/049

Abstract: Systems and methods for predicting system device failure are provided. The method includes representing device failure related data associated with the devices from a predetermined domain by temporal graphs for each of the devices. The method also includes extracting vector representations based on temporal graph features from the temporal graphs that capture both temporal and structural correlation in the device failure related data. The method further includes predicting, based on the vector representations and device failure related metrics in the predetermined domain, one or more of the devices that is expected to fail within a predetermined time.

公开(公告)号：US20230074002A1

公开(公告)日：2023-03-09

申请号：US17892192

申请日：2022-08-22

Applicant: NEC Laboratories America, Inc.

Inventor： Xuchao Zhang ,  Yuncong Chen ,  Haifeng Chen ,  Wenchao Yu ,  Wei Cheng ,  Xujiang Zhao

IPC: G01H3/08 ,  G06N3/04

Abstract: Systems and methods for Evidence-based Sound Event Early Detection is provided. The system/method includes parsing collected labeled audio corpus data and real time audio streaming data utilizing mel-spectrogram, encoding features of the parsed mel-spectrograms using a trained neural network, and generating a final predicted result for a sound event based on the belief, disbelief and uncertainty outputs from the encoded mel-spectrograms.

公开(公告)号：US20230070443A1

公开(公告)日：2023-03-09

申请号：US17896590

申请日：2022-08-26

Applicant: NEC Laboratories America, Inc.

Inventor： Wei Cheng ,  Haifeng Chen ,  Jingchao Ni ,  Wenchao Yu ,  Yuncong Chen ,  Dongsheng Luo

IPC: G06K9/62

Abstract: A computer-implemented method for meta-learning is provided. The method includes receiving a training time series and labels corresponding to some of the training time series. The method further includes optimizing time series augmentations of the training time series using a time series augmentation selection process performed by a meta learner to obtain a selected augmentation from a plurality of candidate augmentations. The method also includes training a time series encoder with contrastive loss using the selected augmentation to obtain a learned time series encoder. The method additionally includes learning, by the learned time series encoder, a vector representation of another time series. The method further includes performing, by the learned time series encoder, a downstream task of label classification for at least a portion of the other time series.

公开(公告)号：US11468262B2

公开(公告)日：2022-10-11

申请号：US16169184

申请日：2018-10-24

Applicant: NEC Laboratories America, Inc.

Inventor： Wei Cheng ,  Haifeng Chen ,  Kenji Yoshihira ,  Wenchao Yu

IPC: G06K9/62 ,  G06N3/04 ,  G06N3/08 ,  G06V10/44

Abstract: Methods and systems for embedding a network in a latent space include generating a representation of an input network graph in the latent space using an autoencoder model and generating a representation of a set of noise samples in the latent space using a generator model. A discriminator model discriminates between the representation of the input network graph and the representation of the set of noise samples. The autoencoder model, the generator model, and the discriminator model are jointly trained by minimizing a joint loss function that includes parameters for each model. A final representation of the input network graph is generated using the trained autoencoder model.

公开(公告)号：US20210232918A1

公开(公告)日：2021-07-29

申请号：US17158092

申请日：2021-01-26

Applicant: NEC Laboratories America, Inc.

Inventor： Wei Cheng ,  Haifeng Chen ,  Wenchao Yu

IPC: G06N3/08 ,  G06N3/04

Abstract: Methods and systems for training a graph neural network (GNN) include training a denoising network in a GNN model, which generates a subgraph of an input graph by removing at least one edge of the input graph. At least one GNN layer in the GNN model, which performs a GNN task on the subgraph, is jointly trained with the denoising network.

公开(公告)号：US20200090025A1

公开(公告)日：2020-03-19

申请号：US16553465

申请日：2019-08-28

Applicant: NEC Laboratories America, Inc.

Inventor： Wei Cheng ,  LuAn Tang ,  Dongjin Song ,  Bo Zong ,  Haifeng Chen ,  Jingchao Ni ,  Wenchao Yu

IPC: G06N3/04 ,  G06N3/08

Abstract: Systems and methods for predicting system device failure are provided. The method includes representing device failure related data associated with the devices from a predetermined domain by temporal graphs for each of the devices. The method also includes extracting vector representations based on temporal graph features from the temporal graphs that capture both temporal and structural correlation in the device failure related data. The method further includes predicting, based on the vector representations and device failure related metrics in the predetermined domain, one or more of the devices that is expected to fail within a predetermined time.

公开(公告)号：US20250148540A1

公开(公告)日：2025-05-08

申请号：US18620099

申请日：2024-03-28

Applicant: NEC Laboratories America, Inc.

Inventor： LuAn Tang ,  Haoyu Wang ,  Haifeng Chen ,  Wenchao Yu ,  Zhengzhang Chen

IPC: G06Q40/08

Abstract: Systems and methods are provided for classifying components include monitoring sensors to collect sensor data related to a state of a plurality of components; processing, by a computing system, the sensor data to generate an action sequence using a transformer-based policy network for each of the components. A risk score is generated for the action sequence using a Generative Adversarial Network (GAN), wherein the GAN includes a generator for generating action sequences and a discriminator to distinguish low-risk action sequences in accordance with a threshold. The low-risk action sequences are associated with components in the plurality of components based on the risk score. A status of the low-risk action sequences is communicated to the components.