公开(公告)号：US20230394304A1

公开(公告)日：2023-12-07

申请号：US18248917

申请日：2020-10-15

Applicant: Robert Bosch GmbH ,  Tsinghua University

Inventor： Jun Zhu ,  Fan Bao ,  Chongxuan Li ,  Kun Xu ,  Hang Su ,  Siliang Lu

IPC: G06N3/08

CPC classification number: G06N3/08

Abstract: A method for training neural networks based on energy-based latent variable models (EBLVMs) includes bi-level optimizations based on a score matching objective. The lower-level optimizes a variational posterior distribution of the latent variables to approximate the true posterior distribution of the EBLVM, and the higher-level optimizes the neural network parameters based on a modified SM objective as a function of the variational posterior distribution. The method is used to train neural networks based on EBLVMs with nonstructural assumptions.

公开(公告)号：US20240185023A1

公开(公告)日：2024-06-06

申请号：US18546842

申请日：2021-03-03

Applicant: Robert Bosch GmbH ,  TSINGHUA UNIVERSITY

Inventor： Bo Zhang ,  Chongxuan Li ,  Hang Su ,  Jun Zhu ,  Ke Su ,  Siliang Lu ,  Ze Cheng

IPC: G06N3/042 ,  G06N3/08

CPC classification number: G06N3/042 ,  G06N3/08

Abstract: A method for visual reasoning. The method includes: providing a network with sets of inputs and sets of outputs, wherein each set of inputs of the sets of inputs mapping to one of a set of outputs corresponding to the set of inputs based on visual information on the set of inputs, and wherein the network comprising a Probabilistic Generative Model (PGM) and a set of modules; determining a posterior distribution over combinations of one or more modules of the set of modules through the PGM, based on the provided sets of inputs and sets of outputs; and applying domain knowledge as one or more posterior regularization constraints on the determined posterior distribution.