ALEXANDRIA, Va., Aug. 12 -- United States Patent no. 12,387,141, issued on Aug. 12, was assigned to Scedastic AI Inc. (Seattle).

"Systems and methods for probabilistic representation-based machine learning" was invented by Kevin Sukmin Son (Seoul, South Korea).

According to the abstract* released by the U.S. Patent & Trademark Office: "An example machine-learning component includes an input layer configured to receive a set of inputs and a probabilistic machine-learning model coupled to the input layer, the probabilistic machine-learning model including a set of nodes sparsely coupled to one another in accordance with associations learned from a set of previously-received inputs. The set of nodes include a first subset configured to gener...