中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

156 records (took 0.027 seconds)

    DEMONSTRATION UNCERTAINTY-BASED ARTIFICIAL INTELLIGENCE MODEL FOR OPEN INFORMATION EXTRACTION
    91.
    发明申请
    DEMONSTRATION UNCERTAINTY-BASED ARTIFICIAL INTELLIGENCE MODEL FOR OPEN INFORMATION EXTRACTION 有权

    公开(公告)号：US20250077848A1

    公开(公告)日：2025-03-06

    申请号：US18817793

    申请日：2024-08-28

    Applicant: NEC Laboratories America, Inc.

    Inventor： Xujiang Zhao ,  Haoyu Wang ,  Zhengzhang Chen ,  Wei Cheng ,  Haifeng Chen ,  Yanchi Liu ,  Chen Ling

    IPC: G06N3/0475 ,  G16H80/00

    Abstract: Systems and methods for a demonstration uncertainty-based artificial intelligence model for open information extraction. A large language model (LLM) can generate initial structured sentences using an initial prompt for a domain-specific instruction extracted from an unstructured text input. Structural similarities between the initial structured sentences and sentences from a training dataset can be determined to obtain structurally similar sentences. The LLM can identify relational triplets from combinations of tokens from generated sentences using and the structurally similar sentences. The relational triplets can be filtered based on a calculated demonstration uncertainty to obtain a filtered triplet list. A domain-specific task can be performed using the filtered triplet list to assist the decision-making process of a decision-making entity.

    OPTIMIZING LARGE LANGUAGE MODELS WITH DOMAIN-ORIENTED MODEL COMPRESSION
    92.
    发明申请
    OPTIMIZING LARGE LANGUAGE MODELS WITH DOMAIN-ORIENTED MODEL COMPRESSION 有权

    公开(公告)号：US20250061334A1

    公开(公告)日：2025-02-20

    申请号：US18805978

    申请日：2024-08-15

    Applicant: NEC Laboratories America, Inc.

    Inventor： Yanchi Liu ,  Wei Cheng ,  Xujiang Zhao ,  Runxue Bao ,  Haifeng Chen ,  Nan Zhang

    IPC: G06N3/082 ,  G06N3/0455

    Abstract: Systems and methods for optimizing large language models (LLM) with domain-oriented model compression. Importance weights for general knowledge in a trained LLM, pretrained with deep learning, can be determined by computing the error when removing a weight from the trained LLM. The trained LLM can be iteratively optimized to obtain a domain-compressed LLM with domain knowledge while maintaining general knowledge by: fine-tuning the trained LLM iteratively with domain knowledge using the importance weights for general knowledge to obtain a fine-tuned LLM; determining importance weights for domain knowledge in the LLM with a regularization term by using gradient descent to optimize parameters when the fine-tuned LLM is trained with domain knowledge; and pruning learned knowledge based on importance weights for domain knowledge. A corrective action can be performed on a monitored entity using the domain-compressed LLM.

    FEDERATED IMITATION LEARNING FOR MEDICAL DECISION MAKING
    93.
    发明申请
    FEDERATED IMITATION LEARNING FOR MEDICAL DECISION MAKING 有权

    公开(公告)号：US20240371521A1

    公开(公告)日：2024-11-07

    申请号：US18649072

    申请日：2024-04-29

    Applicant: NEC Laboratories America, Inc.

    Inventor： Wenchao Yu ,  Haifeng Chen ,  Wei Cheng

    IPC: G16H50/20 ,  G06N3/098

    Abstract: Methods and systems for skill prediction include aggregating locally trained parameters from client systems to generate updated global parameters. Parameterized vectors from the client systems are clustered into prototype clusters. A centroid of each prototype cluster is determined and the parameterized vectors from the client systems are matched to centroids of the prototype clusters to identify sets of updated local prototype vectors. The updated global parameters and the updated local prototype vectors are distributed to the client systems.

    Cross-lingual zero-shot transfer via semantic and synthetic representation learning
    95.
    发明授权
    Cross-lingual zero-shot transfer via semantic and synthetic representation learning 有权

    公开(公告)号：US12050870B2

    公开(公告)日：2024-07-30

    申请号：US17464005

    申请日：2021-09-01

    Applicant: NEC Laboratories America, Inc.

    Inventor： Xuchao Zhang ,  Yanchi Liu ,  Bo Zong ,  Wei Cheng ,  Haifeng Chen ,  Junxiang Wang

    IPC: G06F40/284 ,  G06F40/205 ,  G06F40/295 ,  G06N3/04

    CPC classification number: G06F40/284 ,  G06F40/205 ,  G06F40/295 ,  G06N3/04

    Abstract: A computer-implemented method is provided for cross-lingual transfer. The method includes randomly masking a source corpus and a target corpus to obtain a masked source corpus and a masked target corpus. The method further includes tokenizing, by pretrained Natural Language Processing (NLP) models, the masked source corpus and the masked target corpus to obtain source tokens and target tokens. The method also includes transforming the source tokens and the target tokens into a source dependency parsing tree and a target dependency parsing tree. The method additionally includes inputting the source dependency parsing tree and the target dependency parsing tree into a graph encoder pretrained on a translation language modeling task to extract common language information for transfer. The method further includes fine-tuning the graph encoder and a down-stream network for a specific NLP down-stream task.

    INFORMATION-AWARE GRAPH CONTRASTIVE LEARNING
    97.
    发明公开
    INFORMATION-AWARE GRAPH CONTRASTIVE LEARNING 审中-公开

    公开(公告)号：US20240037402A1

    公开(公告)日：2024-02-01

    申请号：US18484862

    申请日：2023-10-11

    Applicant: NEC Laboratories America, Inc.

    Inventor： Wei Cheng ,  Dongkuan Xu ,  Haifeng Chen

    IPC: G06N3/08

    CPC classification number: G06N3/08

    Abstract: A method for performing contrastive learning for graph tasks and datasets by employing an information-aware graph contrastive learning framework is presented. The method includes obtaining two semantically similar views of a graph coupled with a label for training by employing a view augmentation component, feeding the two semantically similar views into respective encoder networks to extract latent representations preserving both structure and attribute information in the two views, optimizing a contrastive loss based on a contrastive mode by maximizing feature consistency between the latent representations, training a neural network with the optimized contrastive loss, and predicting a new graph label or a new node label in the graph.

    INTERPRETING CONVOLUTIONAL SEQUENCE MODEL BY LEARNING LOCAL AND RESOLUTION-CONTROLLABLE PROTOTYPES
    98.
    发明公开
    INTERPRETING CONVOLUTIONAL SEQUENCE MODEL BY LEARNING LOCAL AND RESOLUTION-CONTROLLABLE PROTOTYPES 审中-公开

    公开(公告)号：US20240028898A1

    公开(公告)日：2024-01-25

    申请号：US18479372

    申请日：2023-10-02

    Applicant: NEC Laboratories America, Inc.

    Inventor： Jingchao Ni ,  Zhengzhang Chen ,  Wei Cheng ,  Bo Zong ,  Haifeng Chen

    IPC: G06N3/08 ,  G06N3/04

    CPC classification number: G06N3/08 ,  G06N3/04

    Abstract: A method interprets a convolutional sequence model. The method converts an input data sequence having input segments into output features. The method clusters the input segments into clusters using respective resolution-controllable class prototypes allocated to each of classes. Each respective class prototype includes a respective output feature subset characterizing a respective associated class. The method calculates, using the clusters, similarity scores that indicate a similarity of an output feature to a respective class prototypes responsive to distances between the output feature and the respective class prototypes. The method concatenates the similarity scores to obtain a similarity vector. The method performs a prediction and prediction support operation that provides a value of prediction and an interpretation for the value responsive to the input segments and similarity vector. The interpretation for the value of prediction is provided using only non-negative weights and lacking a weight bias in the fully connected layer.

    PERSONALIZED FEDERATED LEARNING VIA HETEROGENEOUS MODULAR NETWORKS
    99.
    发明公开
    PERSONALIZED FEDERATED LEARNING VIA HETEROGENEOUS MODULAR NETWORKS 审中-公开

    公开(公告)号：US20230394323A1

    公开(公告)日：2023-12-07

    申请号：US18311984

    申请日：2023-05-04

    Applicant: NEC Laboratories America, Inc.

    Inventor： Wei Cheng ,  Wenchao Yu ,  Xuchao Zhang ,  Haifeng Chen

    IPC: H04L41/16 ,  H04L41/142

    CPC classification number: H04L41/16 ,  H04L41/142

    Abstract: A computer-implemented method for personalizing heterogeneous clients is provided. The method includes initializing a federated modular network including a plurality of clients communicating with a server, maintaining, within the server, a heterogenous module pool having sub-blocks and a routing hypernetwork, partitioning the plurality of clients by modeling a joint distribution of each client into clusters, enabling each client to make a decision in each update to assemble a personalized model by selecting a combination of sub-blocks from the heterogenous module pool, and generating, by the routing hypernetwork, the decision for each client.

Patent Agency Ranking