Patents by Inventor Laurentius Johannes Paulus van der Maaten

Laurentius Johannes Paulus van der Maaten has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Analyzing spatially-sparse data based on submanifold sparse convolutional neural networks
    Patent number: 11544550
    Abstract: In one embodiment, a method includes accessing a plurality of content objects, generating a plurality of voxelized representations for the plurality of content objects, respectively, generating one or more building blocks based on one or more sparse convolutions, which includes determining one or more active sites for each of the plurality of content objects based on the voxelized representation of each of the plurality of content objects and applying the one or more sparse convolutions to the one or more active sites, and training a machine-learning model based on a convolutional network including the one or more building blocks.
    Type: Grant
    Filed: November 16, 2018
    Date of Patent: January 3, 2023
    Assignee: Meta Platforms, Inc.
    Inventors: Benjamin Thomas Graham, Laurentius Johannes Paulus van der Maaten, Martin Helmut Engelcke
  • Analyzing Spatially-Sparse Data Based on Submanifold Sparse Convolutional Neural Networks
    Publication number: 20190156206
    Abstract: In one embodiment, a method includes accessing a plurality of content objects, generating a plurality of voxelized representations for the plurality of content objects, respectively, generating one or more building blocks based on one or more sparse convolutions, which includes determining one or more active sites for each of the plurality of content objects based on the voxelized representation of each of the plurality of content objects and applying the one or more sparse convolutions to the one or more active sites, and training a machine-learning model based on a convolutional network including the one or more building blocks.
    Type: Application
    Filed: November 16, 2018
    Publication date: May 23, 2019
    Inventors: Benjamin Thomas Graham, Laurentius Johannes Paulus van der Maaten, Martin Helmut Engelcke