利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

454 条记录 (耗时 0.041 秒)

    CHOOSING A LARGE LANGUAGE MODEL INTERFACING MECHANISM BASED ON SAMPLE QUESTION EMBEDDINGS
    1.
    发明公开
    CHOOSING A LARGE LANGUAGE MODEL INTERFACING MECHANISM BASED ON SAMPLE QUESTION EMBEDDINGS 审中-公开

    公开(公告)号：US20240362497A1

    公开(公告)日：2024-10-31

    申请号：US18398039

    申请日：2023-12-27

    申请人： Box, Inc.

    发明人： Denis GRENADER ,  Benjamin John Kus

    IPC分类号： G06N5/01 ,  G06N3/0455

    CPC分类号： G06N5/01 ,  G06N3/0455

    摘要： Methods, systems, and computer program products for managing interactions between a content management system (CMS) and a large language model (LLM) system. The semantics of user questions can be considered before prompting an LLM, or alternatively, before querying datasets that are local to the CMS. Given a user question to be answered, the embedding of the user question can be matched against preconfigured sample question embeddings to determine a best match. A prompt corresponding to the determined best match is then configured based on identification of the class or classes that correspond to the matched question. Prompts for provision to LLMs can be synthesized based on a particular user's identity and/or based on the particular user's historical collaboration activities over objects of the CMS. The LLM can be hosted by a third-party provider. Alternatively all or portions of a large language model system can be hosted within the CMS.

    SYSTEM AND METHOD FOR TRAINING AN AUTOENCODER TO DETECT ANOMALOUS SYSTEM BEHAVIOR
    2.
    发明公开
    SYSTEM AND METHOD FOR TRAINING AN AUTOENCODER TO DETECT ANOMALOUS SYSTEM BEHAVIOR 审中-公开

    公开(公告)号：US20240362463A1

    公开(公告)日：2024-10-31

    申请号：US18692629

    申请日：2022-09-15

    申请人： BAE SYSTEMS Plc

    发明人： Samuel Horry ,  Richard Edward John Nicklin ,  Hans-Heinrich Mai

    IPC分类号： G06N3/0455 ,  G06F11/07

    CPC分类号： G06N3/0455 ,  G06F11/0721 ,  G06F11/079

    摘要： The invention relates to a system and method for detecting anomalous system behaviour. The system comprises a plurality of sensors and a trained autoencoder. The method of training comprises: obtaining training data and test data comprising multiple data records for at least one engineering asset which corresponds to the engineering asset whose behaviour is to be classified, wherein the data records comprise a plurality of sensor readings for the engineering asset; fitting the autoencoder to the obtained training data; running the test data through the encoder of the fitted autoencoder to obtain encodings of the test data; generating a plurality of data sets from the obtained encodings, wherein the generated plurality of data sets include under-represented data sets; cloning the fitted autoencoder to create a cloned autoencoder for each of the generated plurality of data sets; and aggregating the cloned autoencoders to form an over-arching autoencoder. The method further comprises calculating an error data set between the training data and data reconstructed by the over-arching auto encoder; obtaining, using the calculated error data set, estimated parameters for calculating an anomaly score for each data record, wherein the anomaly score is selected from a Mahalanobis distance and a squared Mahalanobis distance; and estimating, using the calculated error set, parameters for calculating a decomposition of the anomaly score to identify a contribution from each sensor reading to the anomaly score.

    MULTI-TASK NEURAL NETWORK DESIGN USING TASK CRYSTALIZATION
    7.
    发明公开
    MULTI-TASK NEURAL NETWORK DESIGN USING TASK CRYSTALIZATION 审中-公开

    公开(公告)号：US20240346291A1

    公开(公告)日：2024-10-17

    申请号：US18300807

    申请日：2023-04-14

    申请人： GE Precision Healthcare LLC

    发明人： Xiaomeng Dong ,  Michael Potter ,  Hongxu Yang ,  Ravi Soni ,  Gopal Biligeri Avinash

    IPC分类号： G06N3/0455 ,  G06N3/082

    CPC分类号： G06N3/0455 ,  G06N3/082

    摘要： Techniques are described for multi-task neural network model design using task crystallization are described. In one example a task crystallization method comprises adding one or more task-specific channels to a backbone neural network adapted to perform a primary inferencing task to generate a multi-task neural network model, wherein the adding comprises adding task-specific elements to different layers of the backbone neural network for each channel of the one or more task-specific channels. The method further comprises training, by the system, the one or more task-specific channels to perform one or more additional inferencing tasks that are respectively different from one another and the primary inferencing task, comprising separately tuning and crystallizing the task-specific elements of each channel of the one or more task-specific channels.

    MACHINE LEARNING BASED DEFECT EXAMINATION FOR SEMICONDUCTOR SPECIMENS
    8.
    发明公开
    MACHINE LEARNING BASED DEFECT EXAMINATION FOR SEMICONDUCTOR SPECIMENS 审中-公开

    公开(公告)号：US20240338811A1

    公开(公告)日：2024-10-10

    申请号：US18130845

    申请日：2023-04-04

    申请人： Applied Materials Israel Ltd.

    发明人： Yehonatan Hai OFIR ,  Yotam Nissim BEN SHOSHAN ,  Ran BADANES ,  Boris SHERMAN

    IPC分类号： G06T7/00 ,  G06N3/0455

    CPC分类号： G06T7/001 ,  G06N3/0455 ,  G06T2207/20081 ,  G06T2207/20084

    摘要： There is provided a system and method of examination a semiconductor specimen. The method includes obtaining a runtime image of the specimen; processing the runtime image using a first machine learning (ML) model to extract a set of runtime features representative of a set of patches in the runtime image; and comparing the set of runtime features with a bank of reference features, giving rise to an anomaly map indicative of one or more defective patches in the runtime image. The bank of reference features is previously generated by obtaining a plurality of synthetic reference images generated by a second ML model based on a plurality of actual images; and processing the plurality of synthetic reference images by the first ML model to extract, for each synthetic reference image, a set of reference features representative thereof, giving rise to the bank of reference features.

    System and Methods for Training Machine-Learned Models for Use in Computing Environments with Limited Resources
    9.
    发明公开
    System and Methods for Training Machine-Learned Models for Use in Computing Environments with Limited Resources 审中-公开

    公开(公告)号：US20240338572A1

    公开(公告)日：2024-10-10

    申请号：US18681763

    申请日：2021-08-06

    申请人： Google LLC

    发明人： Nicholas Gillian ,  Lawrence Au

    IPC分类号： G06N3/096 ,  G06N3/0455

    CPC分类号： G06N3/096 ,  G06N3/0455

    摘要： The present disclosure provides computer-implemented methods, systems, and devices for efficient training of models for use in embedded systems. A model training system accesses unlabeled data elements. The model training system trains one or more encoder models for data encoding of using each unlabeled data element as input. The model training system generates an encoded version of each of a plurality of labeled data elements. The model training system trains decoder models for label generation using the encoded version of the second data set as input. The model training system generates provisional labels for the unlabeled data elements in the first data set, such that each unlabeled data element has an associated provisional label. The model training system trains one or more student models using the unlabeled data elements from the first data set and the associated provisional labels.