Patents by Inventor Marco ANCONA

Marco ANCONA 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).

  • Techniques for understanding how trained neural networks operate
    Patent number: 11568212
    Abstract: In various embodiments, a relevance application quantifies how a trained neural network operates. In operation, the relevance application generates a set of input distributions based on a set of input points associated with the trained neural network. Each input distribution is characterized by a mean and a variance associated with a different neuron included in the trained neural network. The relevance application propagates the set of input distributions through a probabilistic neural network to generate at least a first output distribution. The probabilistic neural network is derived from at least a portion of the trained neural network. Based on the first output distribution, the relevance application computes a contribution of a first input point included in the set of input points to a difference between a first output point associated with a first output of the trained neural network and an estimated mean prediction associated with the first output.
    Type: Grant
    Filed: August 6, 2019
    Date of Patent: January 31, 2023
    Assignees: DISNEY ENTERPRISES, INC., ETH ZÜRICH, (EIDGENÖSSISCHE TECHNISCHE HOCHSCHULE ZÜRICH)
    Inventors: Ahmet Cengiz Öztireli, Markus Gross, Marco Ancona
  • TECHNIQUES FOR UNDERSTANDING HOW TRAINED NEURAL NETWORKS OPERATE
    Publication number: 20210042613
    Abstract: In various embodiments, a relevance application quantifies how a trained neural network operates. In operation, the relevance application generates a set of input distributions based on a set of input points associated with the trained neural network. Each input distribution is characterized by a mean and a variance associated with a different neuron included in the trained neural network. The relevance application propagates the set of input distributions through a probabilistic neural network to generate at least a first output distribution. The probabilistic neural network is derived from at least a portion of the trained neural network. Based on the first output distribution, the relevance application computes a contribution of a first input point included in the set of input points to a difference between a first output point associated with a first output of the trained neural network and an estimated mean prediction associated with the first output.
    Type: Application
    Filed: August 6, 2019
    Publication date: February 11, 2021
    Inventors: Ahmet ÖZTIRELI, Markus GROSS, Marco ANCONA