Hybrid Memristor–CMOS Neuromorphic Tile with Adaptive Sleep for Edge Inference

Afifa Tareem , Syeda Hafsa Sadaf , Raheema Sultana Mirza , K priyarika sagar

neuromorphic computing, memristor, CMOS neurons, spiking neural networks, STDP, adaptive sleep, edge AI, DVS

Abstract Edge devices—drones, robots, wearables—require low-latency perception, long battery life, and the ability to adapt locally. Neuromorphic computing, which uses event-driven spiking neural networks and co-located memory and processing, offers a promising path, but practical obstacles remain: compact modular hardware primitives, memristive device non-idealities, and poor energy proportionality when parts of a network are idle. This paper presents a practical design: a hybrid Memristor–CMOS neuromorphic tile that pairs CMOS Leaky–Integrate-and-Fire neurons with memristor crossbar synapses, a hardware-aware STDP learning engine, and an Adaptive Sleep Power Manager (ASPM) to power-gate idle compute while preserving non-volatile synaptic state. The architecture, learning and programming strategy, adaptive-sleep policy, and a reproducible prototyping and evaluation roadmap (simulation → FPGA/emulation → sensor demo) are described. The tile is intended as a modular primitive for building energy-proportional neuromorphic arrays suitable for real-world edge perception tasks.

Published Paper   E-Certificate

"Hybrid Memristor–CMOS Neuromorphic Tile with Adaptive Sleep for Edge Inference", IJEDR - INTERNATIONAL JOURNAL OF ENGINEERING DEVELOPMENT AND RESEARCH (www.IJEDR.org), ISSN:2321-9939, Vol.13, Issue 4, page no.677-683, November-2025, Available :https://rjwave.org/IJEDR/papers/IJEDR2504332.pdf

Volume 13 Issue 4, November-2025

Pages : 677-683

Paper Reg. ID: IJEDR_302398

Published Paper Id: IJEDR2504332

Research Area: Science and Technology

Country: Hyderabad, Telangana, India

Published Paper PDF: https://rjwave.org/IJEDR/papers/IJEDR2504332

Published Paper URL: https://rjwave.org/IJEDR/viewpaperforall?paper=IJEDR2504332

ISSN: 2321-9939 | IMPACT FACTOR: 9.37 Calculated By Google Scholar | ESTD YEAR: 2013

An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 9.37 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator

Publisher: IJEDR (IJ Publication) Janvi Wave

This work is licensed under a Creative Commons Attribution 4.0 International License and The Open Definition