US Patent Issued to Matterport on July 1 for "High-dimensional transfer learning" (California Inventor)

ALEXANDRIA, Va., July 3 -- United States Patent no. 12,346,823, issued on July 1, was assigned to Matterport Inc. (Sunnyvale, Calif.).

"High-dimensional transfer learning" was invented by Matthieu Francois Perrinel (Berkeley, Calif.).

According to the abstract* released by the U.S. Patent & Trademark Office: "An example method comprises applying learning (e.g., weights) developed for training a first model for a first data set of image data to training a second model for a second data set of sensor data. The first and the second data sets may be from the same environment. The second data set has a greater number of channels than the first data set. Weights of layers determined in the first model training may be initially applied to traini...