US Patent Issued to Salesforce on Feb. 18 for "Methods and system for deep learning model generation of samples with enhanced attributes" (Singaporean, American Inventors)

ALEXANDRIA, Va., Feb. 19 -- United States Patent no. 12,229,655, issued on Feb. 18, was assigned to Salesforce Inc. (San Francisco).

"Methods and system for deep learning model generation of samples with enhanced attributes" was invented by Ali Madani (Oakland, Calif.) and Alvin Guo Wei Chan (Singapore).

According to the abstract* released by the U.S. Patent & Trademark Office: "Embodiments described herein provide methods and systems for generating data samples with enhanced attribute values. Some embodiments of the disclosure disclose a deep neural network framework with an encoder, a decoder, and a latent space therebetween, that is configured to extrapolate beyond the attributes of samples in a training distribution to generate data s...