US Patent Issued to Cognitiv on Jan. 13 for "Efficient cross-platform serving of deep neural networks for low latency applications" (California Inventor)

ALEXANDRIA, Va., Jan. 13 -- United States Patent no. 12,524,650, issued on Jan. 13, was assigned to Cognitiv Corp. (New York).

"Efficient cross-platform serving of deep neural networks for low latency applications" was invented by Aaron Andalman (Berkeley, Calif.).

According to the abstract* released by the U.S. Patent & Trademark Office: "Systems, apparatuses, and methods for implementation of an inference or prediction process using a recurrent neural network (RNN) that is particularly advantageous for low-latency applications. Embodiments introduce an implementation of a recurrent neural network-based system which results in a fixed inference time (i.e., a constant computation time to perform an inference stage) that is independent of ...