US Patent Issued to International Business Machines, Rensselaer Polytechnic Institute on Jan. 13 for "Spectral data augmentation for single domain generalization" (New York Inventors)

ALEXANDRIA, Va., Jan. 13 -- United States Patent no. 12,525,006, issued on Jan. 13, was assigned to International Business Machines Corp. (Armonk, N.Y.) and Rensselaer Polytechnic Institute (Troy, N.Y.).

"Spectral data augmentation for single domain generalization" was invented by Pin-Yu Chen (White Plains, N.Y.), Amit Dhurandhar (Yorktown Heights, N.Y.), Jiajin Zhang (Troy, N.Y.), Hanqing Chao (Troy, N.Y.) and Pingkun Yan (Clifton Park, N.Y.).

According to the abstract* released by the U.S. Patent & Trademark Office: "A machine learning model is trained using original source domain data through empirical risk minimization and a model sensitivity map is computed. Each sensitive frequency point on the model sensitivity map is targeted. An ...