ALEXANDRIA, Va., Sept. 24 -- United States Patent no. 12,743,602, issued on Sept. 22, was assigned to Mitsubishi Electric Research Laboratories Inc. (Cambridge, Mass.).

"Automated variational inference using stochastic models with irregular beliefs" was invented by Toshiaki Koike Akino (Belmont, Mass.) and Ye Wang (Andover, Mass.).

According to the abstract* released by the U.S. Patent & Trademark Office: "A system and method for automated construction of a stochastic deep neural network (DNN) architecture is provided. The framework of invention automatically searches for most relevant stochastic modes underlaying datasets for variational Bayesian inference. The invention provides a way to use heterogenous, irregular, and mismatched belie...