18, November 2025

Advancements in Neuromorphic Computing: Exploring the Role of Memristive Devices in Artificial Neural Networks

VOLUME-11; ISSUE-11; NOV-2025

Author(s): Prince Patel

Authors Affiliations:

Assistant Professor, Department of Artificial Intelligence & Data Science, Sankalchand Patel College of Engineering, Visnagar, Gujarat 384315

DOIs:10.2015/IJIRMF/202511008     |     Paper ID: IJIRMF202511008


Abstract
Keywords
Cite this Article/Paper as
References

This study explores the application of Artificial Neural Networks (ANN) in modelling low dimensional hybrid perovskite based memristor devices, crucial for efficient deep learning in the era of AI, big data, cloud computing and IoT. The research involves training and validating the ANN architecture using simulated memristor (resistance vs. pulses) data with a linear drift model. The aim is to identify the optimal ANN configuration by adjusting the proportion of testing data and hidden neurons while optimizing with varying validation data percentages. Given the need for low power consumption and limited chip space in deep learning models, particularly in areas like object detection, natural language processing, and pattern recognition, the study proposes memristor-based object detection on the MNIST dataset. Remarkably, this approach achieves an impressive accuracy of ~ 94%, implemented using the PyTorch module in Python. The study emphasizes the difficulties encountered by computing systems relying on von Neumann architecture, attributed to the constraints in size posed by complementary metal oxide semiconductor (CMOS) transistors in the rapidly advancing fields of artificial intelligence and machine learning.

Memristor, Dion-Jacobson Hybrid Perovskite, Flexible, Resistive Switching, Hebbian Learning, Synaptic Behavior, Pattern recognition, recurrent neural networks, feed forward neural networks, and artificial neural networks

Prince Patel (2025); Advancements in Neuromorphic Computing: Exploring the Role of Memristive Devices in Artificial Neural Networks, International Journal for Innovative Research in Multidisciplinary Field, ISSN(O): 2455-0620, Vol-11, Issue-11, Pp.37-42.          Available on –   https://www.ijirmf.com/

  1. Patel, Mansi, et al. “Insights of BDAPbI4-Based Flexible Memristor for Artificial Synapses and In-Memory Computing.” ACS omega 9.47 (2024): 46841-46850.
  2. Patel, Prince, et al. “Memristor-Based Neuromorphic Computing and Artificial Neural Networks for Computer Vison and AI—Applications.” Biomedical Imaging: Advances in Artificial Intelligence and Machine Learning. Singapore: Springer Nature Singapore, 2024. 307-322.
  3. Midya, Rivu, et al. “Artificial neural network (ANN) to spiking neural network (SNN) converters based on diffusive memristors.” Advanced Electronic Materials 5.9 (2019): 1900060.
  4. Patel, Mansi, et al. “Hybrid Perovskite‐Based Flexible and Stable Memristor by Complete Solution Process for Neuromorphic Computing.” Advanced Electronic Materials 9.4 (2023): 2200908.
  5. Fu, Jingyan, Zhiheng Liao, and Jinhui Wang. “Memristor-based neuromorphic hardware improvement for privacy-preserving ANN.” IEEE Transactions on Very Large Scale Integration (VLSI) Systems 27.12 (2019): 2745-2754.
  6. Ye, Longcheng, et al. “Overview of memristor-based neural network design and applications.” Frontiers in Physics 10 (2022): 839243.
  7. Aguirre, Fernando, et al. “Hardware implementation of memristor-based artificial neural networks.” Nature communications 15.1 (2024): 1974.
  8. Dongale, Tukaram D., et al. “Modelling of nanostructured memristor device characteristics using artificial neural network (ANN).” Journal of Computational Science 11 (2015): 82-90.
  9. Xu, Weilin, Jingjuan Wang, and Xiaobing Yan. “Advances in memristor-based neural networks.” Frontiers in Nanotechnology 3 (2021): 645995.
Post Views: 83

Download Full Paper

Download PDF No. of Downloads:10 | No. of Views: 76