US Patent Issued to EQUIFAX on Nov. 18 for "Machine-learning techniques involving monotonic recurrent neural networks" (Georgia Inventors)

ALEXANDRIA, Va., Nov. 18 -- United States Patent no. 12,475,372, issued on Nov. 18, was assigned to EQUIFAX INC. (Atlanta).

"Machine-learning techniques involving monotonic recurrent neural networks" was invented by Jonathan Boardman (Marietta, Ga.) and Xiao Huang (Marietta, Ga.).

According to the abstract* released by the U.S. Patent & Trademark Office: "Various aspects involve a monotonic recurrent neural network (MRNN) trained for risk assessment or other purposes. For instance, the MRNN is trained to compute a risk indicator from a predictor variable. Training the MRNN includes adjusting weights of nodes of the MRNN subject to a set of monotonicity constraints, wherein the set of monotonicity constraints causes output risk indicators ...