Jason Salavon
U.S. Patent 10,803,347

U.S. Patent 10,803,347 My Genmo neural network architecture was awarded a US patent.  The University of Chicago applied for and owns the rights, I am the inventor.

Fun patent language: An encoder artificial neural network (ANN) may be configured to receive an input image patch and produce a feature vector therefrom.  The encoder ANN may have been trained with a first plurality of domain training images such that an output image patch visually resembling the input image patch can be generated from the feature vector.

A generator ANN may be configured to receive the feature vector and produce a generated image patch from the first feature vector.  The generator ANN may have been trained with feature vectors derived from a first plurality of domain training images and a second plurality of generative training images such that the generated image patch visually resembles the input image patch but is constructed of newly-generated image elements visually resembling one or more image patches from the second plurality of generative training images.

See Genmo & yGAN →

Abstract

U.S. Patent 10,803,347 — 1

Excerpts

U.S. Patent 10,803,347 — 2U.S. Patent 10,803,347 — 3

© Jason Salavon