公开(公告)号：US20250053824A1

公开(公告)日：2025-02-13

申请号：US18933204

申请日：2024-10-31

Applicant: BEIJING BAIDU NETCOM SCIENCE TECHNOLOGY CO., LTD.

Inventor： Xiaofan Li ,  Ji Wan

IPC: G06N3/096

Abstract: Provided a method for training a multi-task fusion detection model includes: obtaining a single-task detection model of each detection task in a detection task set, and obtaining an initial multi-task fusion detection model to be trained based on each single-task detection model; obtaining a training sampling set of the initial multi-task fusion detection model by obtaining a single-task sampling data set of each detection task, in which the training sample set includes a single-task sample and a multi-task sample; and training the initial multi-task fusion detection model according to the single-task sample and/or the multi-task sample until the training is completed, to obtain a trained target multi-task fusion detection model.

公开(公告)号：US12211202B2

公开(公告)日：2025-01-28

申请号：US17500366

申请日：2021-10-13

Applicant: GE Precision Healthcare LLC

Inventor： Deepa Anand ,  Annangi V. Pavan Kumar

IPC: G06T7/00 ,  G06N3/047 ,  G06N3/0475 ,  G06N3/088 ,  G06N3/0895 ,  G06N3/096 ,  G06T7/11 ,  G06V10/25 ,  G06V10/74 ,  G06V10/762 ,  G06V10/774 ,  G06V10/82

Abstract: Techniques are described for learning feature representations of medical images using a self-supervised learning paradigm and employing those feature representations for automating downstream tasks such as image retrieval, image classification and other medical image processing tasks. According to an embodiment, computer-implemented method comprises generating alternate view images for respective medical images included in set of training images using one or more image augmentation techniques or one or more image selection techniques tailored based on domain knowledge associated with the respective medical images. The method further comprises training a transformer network to learn reference feature representations for the respective medical images using their alternate view images and a self-supervised training process. The method further comprises storing the reference feature representations in an indexed data structure with information identifying the respective medical images that correspond to the reference feature representations.

公开(公告)号：US20250005373A1

公开(公告)日：2025-01-02

申请号：US18749887

申请日：2024-06-21

Applicant: NEC Laboratories America, Inc.

Inventor： Junxiang Wang ,  Wei Cheng ,  LuAn Tang ,  Haifeng Chen

IPC: G06N3/096 ,  G06N3/0455 ,  G06N3/084

Abstract: Systems and methods are provided for adapting a model trained from multiple source time-series domains to a target time-series domain, including integrating input data from source time-series domains to pretrain a model with a set of domain-invariant representations, fine-tuning the model by learning prompts specific to each source time-series domain using data from the source time-series domains, and applying instance normalization and segmenting the time-series data into subseries-level normalized patches for the target time-series domain. The normalized patches are fed into a transformer encoder to generate high-dimensional representations of the normalized patches, and a limited number of samples from the target time-series domain are utilized to learn the prompt specific to the target domain. Cosine similarity between the prompt of the target domain and the prompts of source domains is calculated to identify a nearest neighbor prompt, which is utilized for model prediction in the target time-series domain.

公开(公告)号：US20250005371A1

公开(公告)日：2025-01-02

申请号：US18217522

申请日：2023-06-30

Applicant: International Business Machines Corporation

Inventor： Arvind Kumar ,  Mudhakar Srivatsa ,  Raghu Kiran Ganti ,  Joshua M. Rubin

IPC: G06N3/096 ,  G06N3/04

Abstract: A method for training and fine-tuning an artificial intelligence model is disclosed. In one embodiment, such a method distributes, across multiple chiplets of a package, functionality associated with a deep neural network. The method implements, within a first set of chiplets, frozen layers of the deep neural network. By contrast, the method implements, within a second set of chiplets, trainable layers of the deep neural network. The number of chiplets in the second set may be smaller than the number of chiplets in the first set and may consist of a single chiplet in some embodiments. In certain embodiments, the second set of chiplets has one or more of additional memory capacity and additional processing capacity compared to the first set of chiplets in order to train and fine tune the trainable layers. A corresponding apparatus is also disclosed.

公开(公告)号：US20240320510A1

公开(公告)日：2024-09-26

申请号：US18680757

申请日：2024-05-31

Applicant: Souvik Kundu ,  Sharath Nittur Sridhar ,  Sairam Sundaresan

Inventor： Souvik Kundu ,  Sharath Nittur Sridhar ,  Sairam Sundaresan

IPC: G06N3/096

CPC classification number: G06N3/096

Abstract: Systems, apparatus, articles of manufacture, and methods for sensitivity-based fine-tuning of a machine learning model are disclosed. Example instructions cause at least one processor circuit to perform a sensitivity analysis of a foundational model to identify sensitivity scores of respective layers of the foundational model, trim an intermediate layer of the foundational model based on the respective sensitivity score, and fine-tune the trimmed foundational model to create a fine-tuned model, the fine-tuning applied to layers having a respective sensitivity score that meets a threshold sensitivity.

公开(公告)号：US12073937B2

公开(公告)日：2024-08-27

申请号：US17128883

申请日：2020-12-21

Applicant: CANON MEDICAL SYSTEMS CORPORATION

Inventor： Shuhei Bannae ,  Maki Minakuchi ,  Sumie Akiyama ,  Hisaaki Oosako ,  Kohei Shinohara

IPC: G06Q10/00 ,  G06N3/096 ,  G16H30/20 ,  G16H30/40

CPC classification number: G16H30/20 ,  G06N3/096 ,  G16H30/40

Abstract: A medical information processing apparatus according to an embodiment includes a processing circuitry. The processing circuitry is configured: to register first relevance information relevant to a first trained model to be newly generated; to calculate, with respect to each of a plurality of second trained models being existing trained models, a similarity degree between second relevance information relevant to the second trained model and the first relevance information; to calculate a data quantity required to generate the first trained model with respect to each of the plurality of second trained models, on the basis of the similarity degrees each corresponding to a different one of the plurality of second trained models; and to output the data quantity required to generate the first trained model with respect to each of the plurality of second trained models.

公开(公告)号：US20240265267A1

公开(公告)日：2024-08-08

申请号：US18420906

申请日：2024-01-24

Applicant: CORNING INCORPORATED

Inventor： ADAMA TANDIA ,  ZHEREN WANG

IPC: G06N3/096 ,  G06N3/0455

CPC classification number: G06N3/096 ,  G06N3/0455

Abstract: A method of forming a model for predicting one or more properties is provided. The method includes determining a plurality of datasets of properties. The method also includes training a common encoder and one or more individual decoders utilizing the plurality of datasets of properties. Each individual decoder of the individual decoder(s) is distinct from each other and is used to model different properties. The method also includes determining a transfer learning dataset for one or more properties, training a new decoder using the transfer learning dataset and the common encoder, generating a predicted property using the common encoder and the new decoder, and preparing an item using the predicted property.

公开(公告)号：US20240242085A1

公开(公告)日：2024-07-18

申请号：US18410272

申请日：2024-01-11

Applicant: Research & Business Foundation SUNGKYUNKWAN UNIVERSITY

Inventor： Simon Sungil WOO ,  Jeongho KIM

IPC: G06N3/096

CPC classification number: G06N3/096

Abstract: There is provided a deep learning model training method using a self-knowledge distillation algorithm. The method comprises inputting training data to a deep learning model at a first time to obtain first output vectors and inputting the training data to the deep learning model at a second time before the first time to obtain second output vectors; generating soft target vectors at the first time point with respect to the training data using the second output vectors and label data; sorting the first output vectors and the soft target vectors and generating a first partial distribution for the sorted first output vectors and a second partial distribution for the sorted soft target vectors; and training the deep learning model to minimize a first loss function determined on the basis of the first partial distribution and the second partial distribution.

公开(公告)号：US20240220608A1

公开(公告)日：2024-07-04

申请号：US18147773

申请日：2022-12-29

Applicant: Dell Products L.P.

Inventor： OFIR EZRIELEV ,  AMIHAI SAVIR ,  TOMER KUSHNIR

IPC: G06F21/55 ,  G06N3/096

CPC classification number: G06F21/55 ,  G06N3/096

Abstract: Methods and systems for managing artificial intelligence (AI) models are disclosed. To manage AI models, AI models may be updated over time to obtain updated AI model instances. Following each update process, the updated instance of the AI model may be analyzed to determine whether poisoned training data was used to update the AI model. To perform the analysis, characteristics associated with the updated instance of the AI model may be compared to characteristics of the previous instance of the AI model. If the characteristics of the updated instance of the AI model differ from the characteristics of the previous instance of the AI model by an amount dictated by a threshold, the training data used to obtain the updated instance of the AI model may be treated as including poisoned training data.

公开(公告)号：US20240185036A1

公开(公告)日：2024-06-06

申请号：US18522470

申请日：2023-11-29

Applicant: Korea Advanced Institute of Science and Technology

Inventor： Chanyoung PARK ,  Sukwon YUN ,  Kibum KIM ,  Kanghoon YOON

IPC: G06N3/0455 ,  G06N3/096

CPC classification number: G06N3/0455 ,  G06N3/096

Abstract: There is provided a neural network control apparatus. The apparatus comprises a memory; and a processor configured to: classify a target node into a head group or a tail group based on a reference feature value for each class included in a graph structure; determine, if the target node is classified into the head group, a class of the target node by using a first neural network trained to derive embeddings based on a node with a class corresponding to the head group among nodes included in the graph structure; and determine, if the target node is classified into the tail group, a class of the target node by using a second neural network trained to derive embeddings based on a node with a class corresponding to the tail group among nodes included in the graph structure.