Raytheon Company

James Mullen

Philip A Sallee

Franklin R Tanner

Jonathan Goldstein

Rupal Nigam

Discussed herein are devices, systems, and methods for classification using a clustering autoencoder. A method can include obtaining content to be classified by the DNN classifier, and operating the DNN classifier to determine a classification of the received content, the DNN classifier including a clustering classification layer that clusters based on a latent feature vector representation of the content, the classification corresponding to one or more clusters that are closest to the latent feature vector providing the classification and a corresponding confidence.

Deep neural network hardener

Techniques for multi-factor pathfinding are disclosed. A system receives multiple data sets that represent multiple physical properties associated with multiple three-dimensional coordinates of a physical environment. The system generates multiple weighted data layers corresponding to the physical properties, at least by applying weights to the data sets. The system generates a multi-factor costmap for the three-dimensional environment, based at least on the weighted data layers. The system determines a path through the three-dimensional environment, based at least on the multi-factor costmap.

Systems and methods for multi-factor pathfinding

Subject matter regards improving machine learning techniques using informed pseudolabels. A method can include receiving previously assigned labels indicating an expected classification for data, the labels having a specified uncertainty, generating respective pseudolabels for the data based on the previously assigned labels, the data, a class vector determined by an ML model, and a noise model indicating, based on the specified uncertainty, a likelihood of the previously assigned label given the class, and substituting the pseudolabels for the previously assigned labels in a next epoch of training the ML model.

Machine learning using informed pseudolabels

A neural network apparatus includes processing circuitry and memory. The memory stores a plurality of images of a target. The processing circuitry is configured to: access, from the memory, a first image and an identification of a centroid pixel of the target within the first image; generate, based on a geometry of the target and the centroid pixel, a confidence map indicating, for each pixel in the first image, a confidence value that the pixel includes the target; train, using the plurality of images of the target, including the first image and the confidence map, an artificial neural network to identify the target in visual data; and provide an output representing the trained artificial neural network.

Growing community of inventors

Leesburg, VA, United States of America

James Mullen