US Patent Issued to APPLIED BRAIN RESEARCH on Aug. 11 for "Methods and systems for parallelizing computations in recurrently connected artificial neural networks" (Canadian Inventors)

ALEXANDRIA, Va., Aug. 12 -- United States Patent no. 12,705,457, issued on Aug. 11, was assigned to APPLIED BRAIN RESEARCH INC. (Waterloo, Canada).

"Methods and systems for parallelizing computations in recurrently connected artificial neural networks" was invented by Narsimha Chilkuri (Waterloo, Canada) and Christopher David Eliasmith (Waterloo, Canada).

According to the abstract* released by the U.S. Patent & Trademark Office: "The present invention relates to methods and systems for improving the training and inference speed of recurrently connected artificial neural networks by parallelizing application of one or more network layer's recurrent connection weights across all items in the layer's input sequence. More specifically, the pr...