US Patent Issued to GDM Holding on Nov. 4 for "Generating neural network outputs by enriching latent embeddings using self-attention and cross-attention operations" (British Inventors)

ALEXANDRIA, Va., Nov. 6 -- United States Patent no. 12,462,163, issued on Nov. 4, was assigned to GDM Holding LLC (Mountain View, Calif.).

"Generating neural network outputs by enriching latent embeddings using self-attention and cross-attention operations" was invented by Andrew Coulter Jaegle (London) and Joao Carreira (St. Albans, Great Britain).

According to the abstract* released by the U.S. Patent & Trademark Office: "This specification describes a method for using a neural network to generate a network output that characterizes an entity. The method includes: obtaining a representation of the entity as a set of data element embeddings, obtaining a set of latent embeddings, and processing: (i) the set of data element embeddings, and...