US Patent Issued to Google on July 7 for "Training neural networks represented as computational graphs" (California Inventors)

ALEXANDRIA, Va., July 7 -- United States Patent no. 12,675,684, issued on July 7, was assigned to Google LLC (Mountain View, Calif.).

"Training neural networks represented as computational graphs" was invented by Yuan Yu (Cupertino, Calif.) and Manjunath Kudlur Venkatakrishna (San Jose, Calif.).

According to the abstract* released by the U.S. Patent & Trademark Office: "Systems and Methods for training a neural network represented as a computational graph are disclosed. An example method begins with obtaining data representing a computational graph. The computational graph is then augmented to generate a training computational graph for training the neural network using a machine learning training algorithm that includes computing a gradi...