EUVIMEDObjevte EUVIMED
Open access · CC BY 4.0

Memristive Neural Networks-Assisted Training Algorithms: Current State and Future Challenges

Natasa M. Samardzic, Vuk Vranjkovic, Predrag Teodorovic, Jovana Maricic, Sergey Shchanikov, Susanna Gordleeva, Alexey Mikhaylov, Max Talanov, Victor Kazantsev, Rastislav Struharik, Victor Erokhin

Electronics · 2026-10-22 · 15 (21) · 4892

DOI: 10.3390/electronics15214892 ↗

At a glance

Journal article in Electronics, published online on 2026-10-22. Written by Natasa M. Samardzic and 10 co-authors. 324 references. The full text is freely available (open access, CC BY 4.0).

AbstraktBibliografické údajeCiteRelated studies

Abstract (original language)

Existing challenges in modern AI architectures, including the von Neumann bottleneck and high energy demand, have led to increased research efforts towards the development of novel computing paradigms based on memristive technologies. This comprehensive review summarizes algorithmic approaches for training memristive neural networks (MNNs), including Memristive Spiking Neural Networks (MSNNs), integrating solutions implemented on hardware platforms with those developed in software. In contrast to existing reviews that consider algorithmic aspects within the broader context of hardware implementation, this review provides an algorithm-centric perspective, starting from training algorithms and analyzing different approaches to their adaptation to memristive hardware. The survey covers traditional machine learning algorithms such as backpropagation and its enhancements toward hardware-friendly solutions, as well as gradient-free methods, with particular emphasis on algorithms that address device non-idealities. We additionally provide an overview of bio-inspired learning rules, including Spike-Timing Dependent Plasticity (STDP) and reward-modulated STDP, which can be mimicked using memristive devices, along with reinforcement learning algorithms. Special attention is given to biologically plausible models of spiking neuron-astrocyte networks, and their direct implementation in memristive hardware, which significantly increase the efficiency of self-learning algorithms. Finally, this review presents an algorithm-centric perspective on open questions and challenges toward the large-scale implementation of memristive devices in AI systems.

Cite

APA

Samardzic, N. M., Vranjkovic, V., Teodorovic, P., Maricic, J., Shchanikov, S., Gordleeva, S., Mikhaylov, A., Talanov, M., Kazantsev, V., Struharik, R., & Erokhin, V. (2026). Memristive Neural Networks-Assisted Training Algorithms: Current State and Future Challenges. Electronics, 15(21), 4892. https://doi.org/10.3390/electronics15214892

Vancouver

Samardzic NM, Vranjkovic V, Teodorovic P, Maricic J, Shchanikov S, Gordleeva S, et al. Memristive Neural Networks-Assisted Training Algorithms: Current State and Future Challenges. Electronics. 2026;15(21):4892. doi:10.3390/electronics15214892

BibTeX
@article{Samardzic2026,
  author = {Samardzic, Natasa M. and Vranjkovic, Vuk and Teodorovic, Predrag and Maricic, Jovana and Shchanikov, Sergey and Gordleeva, Susanna and Mikhaylov, Alexey and Talanov, Max and Kazantsev, Victor and Struharik, Rastislav and Erokhin, Victor},
  title = {Memristive Neural Networks-Assisted Training Algorithms: Current State and Future Challenges},
  journal = {Electronics},
  year = {2026},
  volume = {15},
  number = {21},
  pages = {4892},
  doi = {10.3390/electronics15214892}
}
Start for free →