ALEXANDRIA, Va., Dec. 31 -- United States Patent no. 12,511,482, issued on Dec. 30, was assigned to D. E. Shaw Research LLC (New York).
"Multi-modal hierarchical tokenization deep neural network" was invented by Paul Maragakis (New York), Andreas Kraemer (Brooklyn, N.Y.), James P. Roney (Cambridge, Mass.) and Peter Skopp (Westport, Conn.).
According to the abstract* released by the U.S. Patent & Trademark Office: "A system is disclosed for encoding a data string of a first modality into a hierarchical tokenized representation for processing by a text-based deep neural network (DNN) trained on a second modality. The data string comprises multiple units, each having one or more attributes. Each attribute is represented in the tokenized stri...