Patents by Inventor Leonidas Lampropoulos

Leonidas Lampropoulos 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).

  • Neural network image classifier
    Patent number: 10007866
    Abstract: A training engine is described which has a memory arranged to access a neural network image classifier, the neural network image classifier having been trained using a plurality of training images from an input space, the training images being labeled for a plurality of classes. The training engine has an adversarial example generator which computes a plurality of adversarial images by, for each adversarial image, searching a region in the input space around one of the training images, the region being one in which the neural network is linear, to find an image which is incorrectly classified into the plurality of classes by the neural network. The training engine has a processor which further trains the neural network image classifier using at least the adversarial images.
    Type: Grant
    Filed: April 28, 2016
    Date of Patent: June 26, 2018
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Antonio Criminisi, Aditya Vithal Nori, Dimitrios Vytiniotis, Osbert Bastani, Leonidas Lampropoulos
  • NEURAL NETWORK IMAGE CLASSIFIER
    Publication number: 20170316281
    Abstract: A training engine is described which has a memory arranged to access a neural network image classifier, the neural network image classifier having been trained using a plurality of training images from an input space, the training images being labeled for a plurality of classes. The training engine has an adversarial example generator which computes a plurality of adversarial images by, for each adversarial image, searching a region in the input space around one of the training images, the region being one in which the neural network is linear, to find an image which is incorrectly classified into the plurality of classes by the neural network. The training engine has a processor which further trains the neural network image classifier using at least the adversarial images.
    Type: Application
    Filed: April 28, 2016
    Publication date: November 2, 2017
    Inventors: Antonio Criminisi, Aditya Vithal Nori, Dimitrios Vytiniotis, Osbert Bastani, Leonidas Lampropoulos