公开(公告)号：US20240346322A1

公开(公告)日：2024-10-17

申请号：US18328514

申请日：2023-06-02

申请人： Paypal, Inc.

发明人： Mahesh Balan Umaithanu ,  Rohith Srinivaas Mohanakrishnan ,  Venkata Subramanian Selvaraj

IPC分类号： G06N3/0895

CPC分类号： G06N3/0895

摘要： Methods and systems are presented for providing a semi-supervised machine learning framework for training a machine learning model using partly mislabeled training data sets. Using the semi-supervised machine learning framework, an iterative training process is performed on the machine learning model, wherein the training data is being adjusted continuously in each iteration for training the machine learning model. During each iteration, the machine learning model is evaluated based on its ability to identify training data that has been mislabeled. The labeling of identified mislabeled training data is corrected before feeding back to the machine learning model in the next training iteration.

公开(公告)号：US20240330446A1

公开(公告)日：2024-10-03

申请号：US18335064

申请日：2023-06-14

申请人： MICROSOFT TECHNOLOGY LICENSING, LLC

发明人： Muhammed Fatih BULUT ,  Lloyd Geoffrey GREENWALD ,  Aditi Kamlesh SHAH ,  Leo Moreno BETTHAUSER ,  Yingqi LIU ,  Ning XIA ,  Siyue WANG

IPC分类号： G06F21/55 ,  G06N3/0895

CPC分类号： G06F21/554 ,  G06N3/0895 ,  G06F2221/034

摘要： Methods and apparatuses for improving the performance and energy efficiency of machine learning systems that generate security specific machine learning models and generate security related information using security specific machine learning models are described. A security specific machine learning model may comprise a security specific large language model (LLM). The security specific LLM may be trained and deployed to generate semantically related security information. The security specific LLM may be pretrained with a security specific data set that was generated using similarity deduplication and long line handling, and with security specific objectives, such as next log line prediction based on host, system, application, and cyber attacker behavior. The security specific large language model may be fine-tuned using a security specific similarity dataset that may be generated to align the security specific LLM to capture similarity between different security events.

公开(公告)号：US20240290022A1

公开(公告)日：2024-08-29

申请号：US18176267

申请日：2023-02-28

申请人： ADOBE INC.

发明人： Yijun LI ,  Yannick HOLD-GEOFFROY ,  Manuel Rodriguez Ladron DE GUEVARA ,  Jose Ignacio Echevarria VALLESPI ,  Daichi ITO ,  Cameron Younger SMITH

IPC分类号： G06T13/40 ,  G06N3/0455 ,  G06N3/0895

CPC分类号： G06T13/40 ,  G06N3/0455 ,  G06N3/0895

摘要： Avatar generation from an image is performed using semi-supervised machine learning. An image space model undergoes unsupervised training from images to generate latent image vectors responsive to image inputs. An avatar parameter space model undergoes unsupervised training from avatar parameter values for avatar parameters to generate latent avatar parameter vectors responsive to avatar parameter value inputs. A cross-modal mapping model undergoes supervised training on image-avatar parameter pair inputs corresponding to the latent image vectors and the latent avatar parameter vectors. The trained image space model generates a latent image vector from an image input. The trained cross-modal mapping model translates the latent image vector to a latent avatar parameter vector. The trained avatar parameter space model generates avatar parameter values from the latent avatar parameter vector. The latent avatar parameter vector can be used to render an avatar having features corresponding to the input image.

公开(公告)号：US20240257253A1

公开(公告)日：2024-08-01

申请号：US18162414

申请日：2023-01-31

申请人： Truist Bank

发明人： Heather Taylor Young

IPC分类号： G06Q40/06 ,  G06F3/0481 ,  G06F3/04842 ,  G06F3/04847 ,  G06N3/0895 ,  G06N3/09 ,  H04L67/306

CPC分类号： G06Q40/06 ,  G06F3/0481 ,  G06F3/04842 ,  G06F3/04847 ,  G06N3/0895 ,  G06N3/09 ,  H04L67/306 ,  H04L67/12

摘要： A computing system and a method for controlling transmission of placement packets to a device include: a storage device storing user profiles and placement packets having associated placement criteria; a processor adapted to be operatively coupled to the device over a communication channel; and an application including executable code causing the processor to run a placement packet generation software application that collects, processes by machine learning and adds to the stored user profiles profile information. Data received from the user device includes user identification corresponding to one of the user profiles and the processor responds by comparing the profile information of the one user profile with the placement criteria, selecting at least one of the placement packets based upon the comparison and transmitting the selected placement packet to the user device with instructions to display an image related to the selected placement packet to the user.

公开(公告)号：US20240249147A1

公开(公告)日：2024-07-25

申请号：US18419340

申请日：2024-01-22

申请人： Arizona Board of Regents on Behalf of Arizona State University ,  PRIME SOLUTIONS GROUP, INC.

发明人： Kristen Jaskie ,  Nolan Vaughn ,  Vivek Sivaraman Narayanaswamy ,  Sahba Zaare ,  Joseph Marvin ,  Andreas Spanias

IPC分类号： G06N3/0895

CPC分类号： G06N3/0895

摘要： A system for Positive and Unlabeled (PU) learning is tailored specifically for a deep learning framework. The system incorporates an adaptive asymmetric loss function based on Modified Logistic Regression paired with a simple linear transform of an output. When only positive and unlabeled images are available for training, the system results in an inductive classifier where no estimate of the class prior is required.

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：US20240212055A1

公开(公告)日：2024-06-27

申请号：US18239737

申请日：2023-08-29

申请人： SAFB Inc.

发明人： Adam Schloss ,  Marc Philip Romm

IPC分类号： G06Q40/08 ,  G06F21/60 ,  G06K7/14 ,  G06N3/0895 ,  G06Q30/018

CPC分类号： G06Q40/08 ,  G06F21/602 ,  G06K7/1417 ,  G06N3/0895 ,  G06Q30/0185

摘要： Disclosed herein are methods and systems related to verifying insurance. An example method may comprise receiving user information associated with a user. The example method may comprise receiving a vehicle identification number (VIN) associated with a vehicle. The example method may comprise transmitting the received VIN to a VIN database. The example method may comprise receiving information about the vehicle from the VIN database. The example method may comprise creating a customized page for the user accessible by a link. The example method may comprise transmitting the link to the user. The example method may comprise receiving a selected insurance carrier associated with the user via the page accessed by the link. The example method may comprise transmitting the user information to a database associated with the selected insurance carrier. The example method may comprise receiving verification of insurance for the user from the database associated with the insurance carrier.

公开(公告)号：US20240169208A1

公开(公告)日：2024-05-23

申请号：US18515872

申请日：2023-11-21

申请人： Korea University Research and Business Foundation

发明人： Seong Whan LEE ,  Heon Gyu KWAK ,  Young Seok KWEON ,  Gi Hwan SHIN ,  Ha Na JO

IPC分类号： G06N3/0895 ,  G06N3/045 ,  G16H50/20 ,  G16H50/30

CPC分类号： G06N3/0895 ,  G06N3/045 ,  G16H50/20 ,  G16H50/30

摘要： An automatic sleep stage classification system for reducing the variation in performance between users using a contrastive learning method according to one embodiment of the present invention includes: a user terminal that measures a user's biosignal and preprocesses the user's measured biosignal; and a classification server that receives the user's preprocessed biosignal from the user terminal, extracts the user's unique biosignal feature, extracts a similar feature by comparing the user's extracted unique biosignal feature and the user's biosignal feature for contrastive learning, and classifies sleep stages based on the extracted similar feature, wherein the user's biosignal includes at least one of the user's electroencephalography (EEG), electrooculography (EOG), electrocardiogramalectromyography (EMG), respiratory effort signals, pulse, oxygen saturation (SpO2), and blood flow.

公开(公告)号：US20240144021A1

公开(公告)日：2024-05-02

申请号：US18341892

申请日：2023-06-27

申请人： Samsung Electronics Co., Ltd.

发明人： Jihye KIM ,  Aristide BARATIN ,  Simon LACOSTE-JULIEN ,  Yan ZHANG

IPC分类号： G06N3/0895

CPC分类号： G06N3/0895

摘要： An apparatus includes: one or more processors configured to: randomly split a training data set into a first training data set comprising a first label assigned to first data and a second training data set comprising a second label assigned to second data; train a first neural network using a semi-supervised learning scheme based on the first training data set comprising the first label, and an unlabeled second training data set; and train a second neural network using the semi-supervised learning scheme based on the second training data set comprising the second label, and an unlabeled first training data set.

公开(公告)号：US20240060906A1

公开(公告)日：2024-02-22

申请号：US18270074

申请日：2021-12-20

申请人： ASML Netherlands B.V.

发明人： Bart Jacobus Martinus TIEMERSMA ,  Alexandru ONOSE ,  Nick VERHEUL ,  Remco DIRKS

IPC分类号： G01N21/95 ,  G03F7/00 ,  G06N3/0455 ,  G06N3/0895

CPC分类号： G01N21/9501 ,  G03F7/70625 ,  G03F7/706839 ,  G06N3/0455 ,  G06N3/0895

摘要： A modular autoencoder model is described. The modular autoencoder model comprises input models configured to process one or more inputs to a first level of dimensionality suitable for combination with other inputs; a common model configured to: reduce a dimensionality of combined processed inputs to generate low dimensional data in a latent space; and expand the low dimensional data in the latent space into one or more expanded versions of the one or more inputs suitable for generating one or more different outputs; output models configured to use the one or more expanded versions of the one or more inputs to generate the one or more different outputs, the one or more different outputs being approximations of the one or more inputs; and a prediction model configured to estimate one or more parameters based on the low dimensional data in the latent space.