利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

15 条记录 (耗时 0.016 秒)

    TRAINING PERCEPTION MODELS USING SYNTHETIC DATA FOR AUTONOMOUS SYSTEMS AND APPLICATIONS
    2.
    发明申请
    TRAINING PERCEPTION MODELS USING SYNTHETIC DATA FOR AUTONOMOUS SYSTEMS AND APPLICATIONS 有权

    公开(公告)号：US20220391766A1

    公开(公告)日：2022-12-08

    申请号：US17827390

    申请日：2022-05-27

    申请人： NVIDIA Corporation

    发明人： David Jesus Acuna Marrero ,  Sanja Fidler ,  Jonah Philion

    IPC分类号： G06N20/00

    摘要： In various examples, systems and methods are disclosed that use a domain-adaptation theory to minimize the reality gap between simulated and real-world domains for training machine learning models. For example, sampling of spatial priors may be used to generate synthetic data that that more closely matches the diversity of data from the real-world. To train models using this synthetic data that still perform well in the real-world, the systems and methods of the present disclosure may use a discriminator that allows a model to learn domain-invariant representations to minimize the divergence between the virtual world and the real-world in a latent space. As such, the techniques described herein allow for a principled approach to learn neural-invariant representations and a theoretically inspired approach on how to sample data from a simulator that, in combination, allow for training of machine learning models using synthetic data.

    Learning to generate synthetic datasets for training neural networks
    4.
    发明授权
    Learning to generate synthetic datasets for training neural networks 有权

    公开(公告)号：US11610115B2

    公开(公告)日：2023-03-21

    申请号：US16685795

    申请日：2019-11-15

    申请人： NVIDIA Corporation

    发明人： Amlan Kar ,  Aayush Prakash ,  Ming-Yu Liu ,  David Jesus Acuna Marrero ,  Antonio Torralba Barriuso ,  Sanja Fidler

    IPC分类号： G06N3/08 ,  G06F16/901 ,  G06T11/60 ,  G06N3/04

    摘要： In various examples, a generative model is used to synthesize datasets for use in training a downstream machine learning model to perform an associated task. The synthesized datasets may be generated by sampling a scene graph from a scene grammar—such as a probabilistic grammar—and applying the scene graph to the generative model to compute updated scene graphs more representative of object attribute distributions of real-world datasets. The downstream machine learning model may be validated against a real-world validation dataset, and the performance of the model on the real-world validation dataset may be used as an additional factor in further training or fine-tuning the generative model for generating the synthesized datasets specific to the task of the downstream machine learning model.

    ARCHITECTURE-AGNOSTIC FEDERATED LEARNING SYSTEM
    7.
    发明申请
    ARCHITECTURE-AGNOSTIC FEDERATED LEARNING SYSTEM 有权

    公开(公告)号：US20220391781A1

    公开(公告)日：2022-12-08

    申请号：US17827446

    申请日：2022-05-27

    申请人： NVIDIA Corporation

    发明人： Or Litany ,  Haggai Maron ,  David Jesus Acuna Marrero ,  Jan Kautz ,  Sanja Fidler ,  Gal Chechik

    IPC分类号： G06N20/20 ,  G06K9/62 ,  G06N7/00

    摘要： A method performed by a server is provided. The method comprises sending copies of a set of parameters of a hyper network (HN) to at least one client device, receiving from each client device in the at least one client device, a corresponding set of updated parameters of the HN, and determining a next set of parameters of the HN based on the corresponding sets of updated parameters received from the at least one client device. Each client device generates the corresponding set of updated parameters based on a local model architecture of the client device.

    LEARNING TO GENERATE SYNTHETIC DATASETS FOR TRANING NEURAL NETWORKS
    9.
    发明申请
    LEARNING TO GENERATE SYNTHETIC DATASETS FOR TRANING NEURAL NETWORKS 审中-公开

    公开(公告)号：US20200160178A1

    公开(公告)日：2020-05-21

    申请号：US16685795

    申请日：2019-11-15

    申请人： NVIDIA Corporation

    发明人： Amlan Kar ,  Aayush Prakash ,  Ming-Yu Liu ,  David Jesus Acuna Marrero ,  Antonio Torralba Barriuso ,  Sanja Fidler

    IPC分类号： G06N3/08 ,  G06F16/901 ,  G06N3/04 ,  G06T11/60

    摘要： In various examples, a generative model is used to synthesize datasets for use in training a downstream machine learning model to perform an associated task. The synthesized datasets may be generated by sampling a scene graph from a scene grammar—such as a probabilistic grammar—and applying the scene graph to the generative model to compute updated scene graphs more representative of object attribute distributions of real-world datasets. The downstream machine learning model may be validated against a real-world validation dataset, and the performance of the model on the real-world validation dataset may be used as an additional factor in further training or fine-tuning the generative model for generating the synthesized datasets specific to the task of the downstream machine learning model.

    ITERATIVE SPATIAL GRAPH GENERATION
    10.
    发明申请
    ITERATIVE SPATIAL GRAPH GENERATION 审中-公开

    公开(公告)号：US20200302250A1

    公开(公告)日：2020-09-24

    申请号：US16825199

    申请日：2020-03-20

    申请人： Nvidia Corporation

    发明人： Hang Chu ,  Daiqing Li ,  David Jesus Acuna Marrero ,  Amlan Kar ,  Maria Shugrina ,  Ming-Yu Liu ,  Antonio Torralba Barriuso ,  Sanja Fidler

    IPC分类号： G06K9/62 ,  G06N3/08 ,  G06N3/04 ,  G06N5/04 ,  G06N20/10 ,  G06N20/20

    摘要： A generative model can be used for generation of spatial layouts and graphs. Such a model can progressively grow these layouts and graphs based on local statistics, where nodes can represent spatial control points of the layout, and edges can represent segments or paths between nodes, such as may correspond to road segments. A generative model can utilize an encoder-decoder architecture where the encoder is a recurrent neural network (RNN) that encodes local incoming paths into a node and the decoder is another RNN that generates outgoing nodes and edges connecting an existing node to the newly generated nodes. Generation is done iteratively, and can finish once all nodes are visited or another end condition is satisfied. Such a model can generate layouts by additionally conditioning on a set of attributes, giving control to a user in generating the layout.