US Patent Issued to INTERNATIONAL BUSINESS MACHINES on Oct. 20 for "Neural network architecture for concurrent learning with antidromic spikes" (Japanese Inventor)

ALEXANDRIA, Va., Oct. 21 -- United States Patent no. 12,770,039, issued on Oct. 20, was assigned to INTERNATIONAL BUSINESS MACHINES Corp. (Armonk, N.Y.).

"Neural network architecture for concurrent learning with antidromic spikes" was invented by Yasunao Katayama (Hachiouji, Japan).

According to the abstract* released by the U.S. Patent & Trademark Office: "A neural network processing system having multiple layers is provided. Each layer includes a bidirectional Synaptic Network Channel (SNC) for concurrently transmitting weighted sums, yF(t)'s and xB(t)'s, as an elastic wave superposition of inputs, xF(t)'s and yB(t)'s, respectively. Each input is multiplied and added with corresponding weights w's encoded in variable splitters and combi...