Differential learning for learning networks

    公开(公告)号:US11468327B2

    公开(公告)日:2022-10-11

    申请号:US16883315

    申请日:2020-05-26

    Abstract: A computer-implemented system is provided that includes a learning network component that determines respective weights assigned to respective node inputs of the learning network in accordance with a learning phase of the learning network and trains a variable separator component to differentially change learning rates of the learning network component. A differential rate component applies at least one update learning rate to adjust at least one weight assigned to at least one of the respective node inputs and applies at least one other update learning rate to adjust the respective weight assigned to at least one other of the respective node inputs in accordance with the variable separator component during the learning phase of the learning network. A differential rate component applies at least one update rate to adjust at least one weight assigned to at least one of the respective node inputs and applies at least one other update rate to adjust the respective weight assigned to at least one other of the respective node inputs in accordance with the learning phase of the learning network.

    SYNTHETIC TRAINING DATA GENERATION FOR IMPROVED MACHINE LEARNING MODEL GENERALIZABILITY

    公开(公告)号:US20220058437A1

    公开(公告)日:2022-02-24

    申请号:US16999665

    申请日:2020-08-21

    Abstract: Systems and techniques that facilitate synthetic training data generation for improved machine learning generalizability are provided. In various embodiments, an element augmentation component can generate a set of preliminary annotated training images based on an annotated source image. In various aspects, a preliminary annotated training image can be formed by inserting at least one element of interest or at least one background element into the annotated source image. In various instances, a modality augmentation component can generate a set of intermediate annotated training images based on the set of preliminary annotated training images. In various cases, an intermediate annotated training image can be formed by varying at least one modality-based characteristic of a preliminary annotated training image. In various aspects, a geometry augmentation component can generate a set of deployable annotated training images based on the set of intermediate annotated training images. In various instances, a deployable annotated training image can be formed by varying at least one geometric characteristic of an intermediate annotated training image. In various embodiments, a training component can train a machine learning model on the set of deployable annotated training images.

    Deep neural network based identification of realistic synthetic images generated using a generative adversarial network

    公开(公告)号:US11049239B2

    公开(公告)日:2021-06-29

    申请号:US16370082

    申请日:2019-03-29

    Abstract: Techniques are provided for deep neural network (DNN) identification of realistic synthetic images generated using a generative adversarial network (GAN). According to an embodiment, a system is described that can comprise a memory that stores computer executable components and a processor that executes the computer executable components stored in the memory. The computer executable components can comprise, a first extraction component that extracts a subset of synthetic images classified as non-real like as opposed to real-like, wherein the subset of synthetic images were generated using a GAN model. The computer executable components can further comprise a training component that employs the subset of synthetic images and real images to train a DNN network model to classify synthetic images generated using the GAN model as either real-like or non-real like.

    DETERMINING CONFIDENT DATA SAMPLES FOR MACHINE LEARNING MODELS ON UNSEEN DATA

    公开(公告)号:US20200349434A1

    公开(公告)日:2020-11-05

    申请号:US16934650

    申请日:2020-07-21

    Abstract: Techniques are provided for determining confident data samples for machine learning (ML) models on unseen data. In one embodiment, a method is provided that comprises extracting, by a system comprising a processor, a feature vector for a data sample based on projection of the data sample onto a standard feature space. The method further comprises processing, by the system, the feature vector using an outlier detection model to determine whether the data sample is within a scope of a training dataset used to train a machine learning model, wherein the outlier detection model was trained using features extracted from the training dataset based on projection of data samples included in the training dataset onto the standard feature space.

Patent Agency Ranking