利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

191 条记录 (耗时 0.029 秒)

    Generating and managing deep tensor neural networks
    2.
    发明授权
    Generating and managing deep tensor neural networks 有权

    公开(公告)号：US11948093B2

    公开(公告)日：2024-04-02

    申请号：US17938131

    申请日：2022-10-05

    申请人： International Business Machines Corporation ,  Trustees of Tufts College ,  Ramot at Tel-Aviv University Ltd.

    发明人： Lior Horesh ,  Elizabeth Newman ,  Misha E. Kilmer ,  Haim Avron

    IPC分类号： G06N3/084 ,  G06N3/048 ,  G06N3/126

    CPC分类号： G06N3/126 ,  G06N3/048 ,  G06N3/084

    摘要： Techniques for generating and managing, including simulating and training, deep tensor neural networks are presented. A deep tensor neural network comprises a graph of nodes connected via weighted edges. A network management component (NMC) extracts features from tensor-formatted input data based on tensor-formatted parameters. NMC evolves tensor-formatted input data based on a defined tensor-tensor layer evolution rule, the network generating output data based on evolution of the tensor-formatted input data. The network is activated by non-linear activation functions, wherein the weighted edges and non-linear activation functions operate, based on tensor-tensor functions, to evolve tensor-formatted input data. NMC trains the network based on tensor-formatted training data, comparing output training data output from the network to simulated output data, based on a defined loss function, to determine an update. NMC updates the network, including weight and bias parameters, based on the update, by application of tensor-tensor operations.

    Tensor-based predictions from analysis of time-varying graphs
    5.
    发明授权
    Tensor-based predictions from analysis of time-varying graphs 有权

    公开(公告)号：US11386507B2

    公开(公告)日：2022-07-12

    申请号：US16579454

    申请日：2019-09-23

    申请人： International Business Machines Corporation ,  TRUSTEES OF TUFTS COLLEGE ,  Ramot at Tel-Aviv University Ltd.

    发明人： Lior Horesh ,  Osman Asif Malik ,  Shashanka Ubaru ,  Misha E. Kilmer ,  Haim Avron

    IPC分类号： G06Q50/00 ,  G06F17/16 ,  G06N20/00 ,  G06F16/901

    摘要： A computer-implemented method for analyzing a time-varying graph is provided. The time-varying graph includes nodes representing elements in a network, edges representing transactions between elements, and data associated with the nodes and the edges. The computer-implemented method includes constructing, using a processor, adjacency and feature matrices describing each node and edge of each time-varying graph for stacking into an adjacency tensor and describing the data of each time-varying graph for stacking into a feature tensor, respectively. The adjacency and feature tensors are partitioned into adjacency and feature training tensors and into adjacency and feature validation tensors, respectively. An embedding model and a prediction model are created using the adjacency and feature training tensors. The embedding and prediction models are validated using the adjacency and feature validation tensors to identify an optimized embedding-prediction model pair.

    Matrix sketching using analog crossbar architectures
    9.
    发明授权
    Matrix sketching using analog crossbar architectures 有权

    公开(公告)号：US11520855B2

    公开(公告)日：2022-12-06

    申请号：US16874819

    申请日：2020-05-15

    申请人： INTERNATIONAL BUSINESS MACHINES CORPORATION ,  Ramot at Tel-Aviv University Ltd.

    发明人： Lior Horesh ,  Oguzhan Murat Onen ,  Haim Avron ,  Tayfun Gokmen ,  Vasileios Kalantzis ,  Shashanka Ubaru

    IPC分类号： G06F17/16 ,  G06N3/063 ,  G06F17/18

    摘要： A computer-implemented method is presented for performing matrix sketching by employing an analog crossbar architecture. The method includes low rank updating a first matrix for a first period of time, copying the first matrix into a dynamic correction computing device, switching to a second matrix to low rank update the second matrix for a second period of time, as the second matrix is low rank updated, feeding the first matrix with first stochastic pulses to reset the first matrix back to a first matrix symmetry point, copying the second matrix into the dynamic correction computing device, switching back to the first matrix to low rank update the first matrix for a third period of time, and as the first matrix is low rank updated, feeding the second matrix with second stochastic pulses to reset the second matrix back to a second matrix symmetry point.