MUMBAI, India, Nov. 2 -- Intellectual Property India has published a patent application (202641125875 A) filed by Srm Trp Engineering College on October 22, 2026, for To Implement A Reliable Channel Rsr Spiking Neuron For Energy Efficient Neuromorphic Robotic Application.
Inventors include R. Pranesh Rajan; M. Viswanath; P. Yogeshwara Kumaran; and Dr. A. Sugantha.
The application for the patent was published on October 30, 2026, under issue no. 44/2026.
Abstract: A digital implementation of a resting-potential-adjustable soft-reset (RSR) spiking neuron is disclosed for use as a hardware neuron in neuromorphic and robotic processing. The implementation accumulates a digital input current with a stored membrane-potential state and compares the resulting value with a configurable firing threshold. When the threshold is reached or exceeded, a spike is generated and the stored state is reduced by a reset-adjustment parameter TDP so that residual membrane-potential information is retained. The project implementation is described in Verilog/SystemVerilog and is evaluated through RTL simulation and FPGA synthesis/implementation using Vivado, with an intended Digilent Arty A7-100T target. HR, SR, and RSR behaviors and threshold conditions can be compared. The present document does not treat unverified board-level power measurements as established results.
Disclaimer: Curated by HT Syndication.
