MUMBAI, India, Feb. 27 -- Intellectual Property India has published a patent application (202641017672 A) filed by Ramachandra College Of Engineering, Eluru, Andhra Pradesh, on Feb. 17, for 'an energy-efficient neuromorphic ai framework employing spiking neural networks and memristor-based synapses.'
Inventor(s) include Victor Babu Penumala; Dr. K. Swetha Sastry; and Dr. A Chiranjeevi.
The application for the patent was published on Feb. 27, under issue no. 09/2026.
According to the abstract released by the Intellectual Property India: "This invention introduces a groundbreaking neuromorphic computing framework designed to transform advanced machine learning by emulating the human brain's neural structures and adaptive learning processes. Dubbed Neuro Forge, the system integrates spiking neural networks (SNNs) with memristor-based hardware to enable energy-efficient, real-time AI processing that surpasses traditional von Neumann architectures. Key innovations include dendritic-inspired processing units for enhanced pattern recognition and synaptic plasticity mechanisms for lifelong learning without catastrophic forgetting. Through a hybrid software-hardware pipeline, Neuro Forge achieves up to 100x reductions in power consumption while boosting accuracy in tasks like object detection and natural language processing. Extensive simulations and prototype tests on edge devices demonstrate superior performance over conventional deep neural networks, paving the way for scalable, brain-like AI in resource-constrained environments."
Disclaimer: Curated by HT Syndication.
