知搜-全球专利检索

  1. 登录
  2. 注册

搜索结果

103 条记录 (耗时 0.055 秒)

    TARGETED INCREMENTAL GROWTH WITH CONTINUAL LEARNING IN DEEP NEURAL NETWORKS
    1.
    发明公开
    TARGETED INCREMENTAL GROWTH WITH CONTINUAL LEARNING IN DEEP NEURAL NETWORKS 审中-公开

    公开(公告)号：US20230385608A1

    公开(公告)日：2023-11-30

    申请号：US18327527

    申请日：2023-06-01

    申请人： D5AI LLC

    发明人： James K. BAKER ,  Bradley J. BAKER

    IPC分类号： G06N3/045

    CPC分类号： G06N3/045

    摘要： Computer systems and computer-implemented methods train a neural network, by: (a) computing for each datum in a set of training data, activation values for nodes in the neural network and estimates of partial derivatives of an objective function for the neural network for the nodes in the neural network; (b) selecting a target node of the neural network and/or a target datum in the set of training data; (c) selecting a target-specific improvement model for the neural network, wherein the target-specific improvement model, when added to the neural network, improves performance of the neural network for the target node and/or the target datum, as the case may be; (d) training the target-specific improvement model; (e)merging the target-specific improvement model with the neural network to form an expanded neural network; and (f) training the expanded neural network.

    DIVERSITY FOR DETECTION AND CORRECTION OF ADVERSARIAL ATTACKS
    3.
    发明公开
    DIVERSITY FOR DETECTION AND CORRECTION OF ADVERSARIAL ATTACKS 审中-公开

    公开(公告)号：US20230289434A1

    公开(公告)日：2023-09-14

    申请号：US18005916

    申请日：2021-11-16

    申请人： D5AI LLC

    发明人： James K. BAKER

    IPC分类号： G06F21/55

    CPC分类号： G06F21/55

    摘要： A diverse set of neural networks are trained to be individually robust against adversarial attacks and diverse in a manner that decreases the ability of an adversarial example to fool the full diverse set. The systems/methods use a diversity criterion that is specialized for measuring diversity in response to adversarial attacks rather than diversity in the classification results. Also, one or more networks can be trained that are less robust to adversarial attacks to use as a diagnostic to detect the presence of an adversarial attack. Also, node-to-node relation regularization links can be used to train diverse networks that are randomly selected from a family of diverse networks with exponentially many members.

    DEEP NEURAL NETWORK WITH COMPOUND NODE FUNCTIONING AS A DETECTOR AND REJECTER
    4.
    发明公开
    DEEP NEURAL NETWORK WITH COMPOUND NODE FUNCTIONING AS A DETECTOR AND REJECTER 审中-公开

    公开(公告)号：US20230142528A1

    公开(公告)日：2023-05-11

    申请号：US18147313

    申请日：2022-12-28

    申请人： D5AI LLC

    发明人： James K. Baker

    IPC分类号： G06N3/082 ,  G06N3/044 ,  G06N3/084

    CPC分类号： G06N3/082 ,  G06N3/044 ,  G06N3/084

    摘要： Computer systems and methods modify a base deep neural network (DNN). The method comprises replacing the target node of the base DNN with a compound node to thereby create a modified base DNN. The compound node comprises at least first and second nodes. The first node is trained to detect target node patterns in inputs to the first node and the second node is trained to detect an absence of the target node patterns in inputs to the second node, and the first and second nodes are trained to be non-complementary. Replacing the target node with the compound node comprises: connecting the first node to the upper sub-network of the base DNN, such that the first node has a weighted connection for each of the one or more base connection that the target node had to the upper sub-network in the base DNN; and connecting the second node to the upper sub-network of the base deep DNN, such that the second node has a weighted connection for each of the one or more base connection that the target node had to the upper sub-network in the base deep DNN. After replacing the target node, the modified base DNN is trained.

    Knowledge sharing for machine learning systems
    5.
    发明授权
    Knowledge sharing for machine learning systems 有权

    公开(公告)号：US11610130B2

    公开(公告)日：2023-03-21

    申请号：US17654187

    申请日：2022-03-09

    申请人： D5AI LLC

    发明人： James K. Baker

    IPC分类号： G06N3/08 ,  G06K9/62 ,  G06N3/04 ,  G06N3/084 ,  G06N3/082

    摘要： A machine learning system includes a coach machine learning system that uses machine learning to help a student machine learning system learn its system. By monitoring the student learning system, the coach machine learning system can learn (through machine learning techniques) “hyperparameters” for the student learning system that control the machine learning process for the student learning system. The machine learning coach could also determine structural modifications for the student learning system architecture. The learning coach can also control data flow to the student learning system.

    SELECTIVE TRAINING OF DEEP LEARNING MODULES
    6.
    发明申请
    SELECTIVE TRAINING OF DEEP LEARNING MODULES 有权

    公开(公告)号：US20220383111A1

    公开(公告)日：2022-12-01

    申请号：US17753727

    申请日：2020-09-09

    申请人： D5AI LLC

    发明人： James K. Baker

    IPC分类号： G06N3/08

    摘要： Machine-learning computer system breaks a neural network into a plurality of modules and tracks the training process module-by-module and datum-by-datum, recording auxiliary information during one iteration of the training process for retrieval during a later iteration. Based on this auxiliary information, the computer system can make decisions that can greatly reduce the amount of computation required by the training process. The auxiliary information allows the computer system to diagnose and fix problems that occur during the training process on a module-by-module and/or datum-by-datum basis.

    DEEP LEARNING WITH JUDGMENT
    7.
    发明申请
    DEEP LEARNING WITH JUDGMENT 有权

    公开(公告)号：US20220335296A1

    公开(公告)日：2022-10-20

    申请号：US17753061

    申请日：2020-07-28

    申请人： D5AI LLC

    发明人： James K. Baker

    IPC分类号： G06N3/08 ,  G06N3/04

    摘要： Computer systems and computer-implemented methods modify a machine learning network, such as a deep neural network, to introduce judgment to the network. A “combining” node is added to the network, to thereby generate a modified network, where activation of the combining node is based, at least in part, on output from a subject node of the network. The computer system then trains the modified network by, for each training data item in a set of training data, performing forward and back propagation computations through the modified network, where the backward propagation computation through the modified network comprises computing estimated partial derivatives of an error function of an objective for the network, except that the combining node selectively blocks back-propagation of estimated partial derivatives to the subject node, even though activation of the combining node is based on the activation of the subject node.

    Efficiently building deep neural networks
    9.
    发明授权
    Efficiently building deep neural networks 有权

    公开(公告)号：US11074502B2

    公开(公告)日：2021-07-27

    申请号：US16620052

    申请日：2019-08-12

    申请人： D5AI LLC

    发明人： James K. Baker

    IPC分类号： G06N3/08 ,  G06N3/04 ,  G06N3/063

    摘要： A computer system uses a pool of predefined functions and pre-trained networks to accelerate the process of building a large neural network or building a combination of (i) an ensemble of other machine learning systems with (ii) a deep neural network. Copies of a predefined function node or network may be placed in multiple locations in a network being built. In building a neural network using a pool of predefined networks, the computer system only needs to decide the relative location of each copy of a predefined network or function. The location may be determined by (i) the connections to a predefined network from source nodes and (ii) the connections from a predefined network to nodes in an upper network. The computer system may perform an iterative process of selecting trial locations for connecting arcs and evaluating the connections to choose the best ones.

    BUILDING DEEP LEARNING ENSEMBLES WITH DIVERSE TARGETS
    10.
    发明申请
    BUILDING DEEP LEARNING ENSEMBLES WITH DIVERSE TARGETS 有权

    公开(公告)号：US20210174265A1

    公开(公告)日：2021-06-10

    申请号：US17268660

    申请日：2019-08-12

    申请人： D5AI LLC

    发明人： James K. BAKER

    IPC分类号： G06N20/20 ,  G06N3/04 ,  G06N3/08 ,  G06N3/063

    摘要： A computer-implemented method of training an ensemble machine learning system comprising a plurality of ensemble members. The method includes selecting a shared objective and an objective for each of the ensemble members. The method further includes training each of the ensemble members according to each objective on a training data set, connecting an output of each of the ensemble members to a joint optimization machine learning system to form a consolidated machine learning system, and training the consolidated machine learning system according to the shared objective and the objective for each of the ensemble members on the training data set. The ensemble members can be the same or different types of machine learning systems. Further, the joint optimization machine learning system can be the same or a different type of machine learning system than the ensemble members.