Memristor Devices and Systems for Neuromorphic Computing

Dear Colleagues,

This Special Issue is dedicated to addressing the critical challenges and exploring the transformative opportunities in the field of memristor technology, with a concentrated focus on its pivotal role in enabling next-generation neuromorphic computing and in-memory processing paradigms. As the demand for energy-efficient and real-time intelligent processing surges across applications from edge computing to large-scale data centers, the limitations of traditional von Neumann architectures become increasingly apparent. Memristors, with their intrinsic properties of non-volatility, analog programmability, and nanoscale scalability, offer a compelling pathway to overcome these bottlenecks. However, a pivotal challenge lies in translating these promising device-level characteristics into reliable, robust, and scalable computing systems. Key obstacles such as device-to-device and cycle-to-cycle variability, limited endurance, stochastic switching behavior, and the complexities of integration into high-density crossbar arrays significantly impede system-level performance and practical deployment. These hardware-centric issues, if not comprehensively understood and mitigated, can fundamentally undermine the computational accuracy, efficiency, and long-term viability of memristor-based solutions. Therefore, this Special Issue seeks contributions that advance the field from fundamental device physics to functional system prototypes, fostering the co-design of materials, devices, circuits, algorithms, and architectures. The goal is to solidify the foundation for a new era of brain-inspired, energy-efficient intelligent systems capable of tackling complex cognitive tasks in our data-driven world.

Areas of focus encompass, but are not limited to, the following:

• Advanced Memristive Materials and Device Engineering: innovations in material stacks, switching mechanisms, and device structures aimed at improving critical metrics: uniformity, endurance (write/erase cycles), retention, analog conductance modulation linearity/symmetry, and switching speed for synaptic and neuronal emulation.
• Robust Circuit and System Architecture Design: novel circuit designs, fault-tolerant architectures, and innovative memory array organizations (e.g., crossbar, 3D integration) that mitigate device non-idealities, sneak-path currents, IR drop, and peripheral circuit overhead, enabling reliable vector–matrix multiplication and other core operations.
• Algorithm–Hardware Co-Design for Neuromorphic Computing: development of specialized training algorithms (e.g., in situ, online, or federated learning), novel neural network models (including spiking neural networks), and adaptive resilience strategies tailored for the precise characteristics, constraints, and noise profiles of memristor hardware platforms.
• System Integration, Prototyping, and Benchmarking: research on full-stack integration, from device interfacing to compiler and software toolchains. Experimental demonstrations and benchmark studies of memristor-based accelerators for applications in edge AI, signal/image processing, scientific computing, and combinatorial optimization.
• Modeling, Characterization, and Reliability Analysis: theoretical and experimental studies on device physics, switching kinetics, scaling limits, thermal effects, and long-term reliability under various operational stresses. Cross-layer modeling frameworks that connect device behavior to system-level performance and lifetime.

Prof. Dr. Ling Li
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 250 words) can be sent to the Editorial Office for assessment.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Electronics is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.