US Patent Issued to DeepMind Technologies on March 4 for "Machine learning systems with memory based parameter adaptation for learning fast and slower" (British Inventors)

ALEXANDRIA, Va., March 5 -- United States Patent no. 12,242,947, issued on March 4, was assigned to DeepMind Technologies Ltd. (London).

"Machine learning systems with memory based parameter adaptation for learning fast and slower" was invented by Pablo Sprechmann (London), Siddhant Jayakumar (London), Jack William Rae (London), Alexander Pritzel (London), Adria Puigdomenech Badia (London), Oriol Vinyals (London), Razvan Pascanu (London) and Charles Blundell (London).

According to the abstract* released by the U.S. Patent & Trademark Office: "There is described herein a computer-implemented method of processing an input data item. The method comprises processing the input data item using a parametric model to generate output data, wherein...