Modern computation based on von Neumann architecture is now a mature cutting-edge science. In the von Neumann architecture, processing and memory units are implemented as separate blocks interchanging data intensively and continuously. This data transfer is responsible for a large part of the power consumption. The next generation computer technology is expected to solve problems at the exascale with 1018 calculations each second. Even though these future computers will be incredibly powerful, if they are based on von Neumann type architectures, they will consume between 20 and 30 megawatts of power and will not have intrinsic physically built-in capabilities to learn or deal with complex data as our brain does. These needs can be addressed by neuromorphic computing systems which are inspired by the biological concepts of the human brain. This new generation of computers has the potential to be used for the storage and processing of large amounts of digital information with much lower power consumption than conventional processors. Among their potential future applications, an important niche is moving the control from data centers to edge devices. The aim of this roadmap is to present a snapshot of the present state of neuromorphic technology and provide an opinion on the challenges and opportunities that the future holds in the major areas of neuromorphic technology, namely materials, devices, neuromorphic circuits, neuromorphic algorithms, applications, and ethics. The roadmap is a collection of perspectives where leading researchers in the neuromorphic community provide their own view about the current state and the future challenges for each research area. We hope that this roadmap will be a useful resource by providing a concise yet comprehensive introduction to readers outside this field, for those who are just entering the field, as well as providing future perspectives for those who are well established in the neuromorphic computing community.
Purpose-led Publishing is a coalition of three not-for-profit publishers in the field of physical sciences: AIP Publishing, the American Physical Society and IOP Publishing.
Together, as publishers that will always put purpose above profit, we have defined a set of industry standards that underpin high-quality, ethical scholarly communications.
We are proudly declaring that science is our only shareholder.
ISSN: 2634-4386
Neuromorphic Computing and Engineering is a multidisciplinary, open access journal publishing cutting edge research on the design, development and application of artificial neural networks and systems from both a hardware and computational perspective. For detailed information about subject coverage see the About the journal section.
Stay informed about the latest journal news and announcements
- The following article is Open access2022 roadmap on neuromorphic computing and engineering
Dennis V Christensen et al 2022 Neuromorph. Comput. Eng. 2 022501
- The following article is Open accessHands-on reservoir computing: a tutorial for practical implementation
Matteo Cucchi et al 2022 Neuromorph. Comput. Eng. 2 032002
View article, Hands-on reservoir computing: a tutorial for practical implementationPDF, Hands-on reservoir computing: a tutorial for practical implementationThis manuscript serves a specific purpose: to give readers from fields such as material science, chemistry, or electronics an overview of implementing a reservoir computing (RC) experiment with her/his material system. Introductory literature on the topic is rare and the vast majority of reviews puts forth the basics of RC taking for granted concepts that may be nontrivial to someone unfamiliar with the machine learning field (see for example reference Lukoševičius (2012 Neural Networks: Tricks of the Trade (Berlin: Springer) pp 659–686). This is unfortunate considering the large pool of material systems that show nonlinear behavior and short-term memory that may be harnessed to design novel computational paradigms. RC offers a framework for computing with material systems that circumvents typical problems that arise when implementing traditional, fully fledged feedforward neural networks on hardware, such as minimal device-to-device variability and control over each unit/neuron and connection. Instead, one can use a random, untrained reservoir where only the output layer is optimized, for example, with linear regression. In the following, we will highlight the potential of RC for hardware-based neural networks, the advantages over more traditional approaches, and the obstacles to overcome for their implementation. Preparing a high-dimensional nonlinear system as a well-performing reservoir for a specific task is not as easy as it seems at first sight. We hope this tutorial will lower the barrier for scientists attempting to exploit their nonlinear systems for computational tasks typically carried out in the fields of machine learning and artificial intelligence. A simulation tool to accompany this paper is available online7.
- The following article is Open accessReal-time chirp-based seizure detection in human iEEG with neuromorphic hardware
Flavia Davidhi et al 2026 Neuromorph. Comput. Eng. 6 034008
View article, Real-time chirp-based seizure detection in human iEEG with neuromorphic hardwarePDF, Real-time chirp-based seizure detection in human iEEG with neuromorphic hardwareEpilepsy affects millions worldwide, with therapy often relying on inaccurate diaries. Chirp patterns in intracranial EEG (iEEG) are specific markers of seizure onset. We present a seizure detection system that can detect iEEG chirp patterns in real-time using a spiking neural network (SNN) implemented on mixed-signal neuromorphic hardware. We validated the system with long-term iEEG recordings from 7 patients with focal epilepsy, filtering signals into patient-specific frequency bands and encoding them with asynchronous pulses. The SNN model implemented on the neuromorphic hardware was configured to detect the chirps as high-to-low frequency sequences. Across 492 h and 62 seizures, the hardware system achieved a sensitivity of 90%, with favourable false alarm rates in 5 patients (<1.3 d−1) and higher rates in 2 others (>10 d−1). There was a median 3.1% overhead in the communication delay of streaming pre-encoded data to the chip. Power consumption of the SNN was low (< 65 µW). Our neuromorphic chirp detection setup demonstrates feasibility for low-power, continuous seizure monitoring, offering a promising approach for wearable or implantable devices.
- The following article is Open accessEvent-driven neuromorphic vision enables energy-efficient visual place recognition
Geoffroy Keime et al 2026 Neuromorph. Comput. Eng. 6 034007
View article, Event-driven neuromorphic vision enables energy-efficient visual place recognitionPDF, Event-driven neuromorphic vision enables energy-efficient visual place recognitionReliable visual place recognition (VPR) under dynamic real-world conditions is critical for autonomous robots, yet conventional deep networks remain limited by high computational and energy demands. Inspired by the mammalian navigation system, we introduce SpikeVPR, a bio-inspired neuromorphic framework that leverages event-based cameras and spiking neural networks (SNNs) to learn compact, invariant place descriptors from a limited number of exemplars, enabling robust VPR across severe changes in illumination, viewpoint, and appearance. SpikeVPR is trained end-to-end using surrogate gradient learning and incorporates EventDilation, a novel augmentation strategy enhancing robustness to speed and temporal variations. Across three challenging benchmarks (Brisbane-Event-VPR, NSAVP and NYC-Event-VPR), SpikeVPR matches the performance of state-of-the-art deep networks while reducing model size by 50
and lowering estimated energy consumption by 30–250, based on an analytical energy model, enabling efficient real-time deployment on mobile and neuromorphic hardware. These results demonstrate that spike-based coding offers an efficient pathway toward robust VPR in complex, changing environments. - The following article is Open accessFew-shot, continual learning for spiking neuromorphic olfaction
Kevin Max and Yang Shen 2026 Neuromorph. Comput. Eng. 6 034013
View article, Few-shot, continual learning for spiking neuromorphic olfactionPDF, Few-shot, continual learning for spiking neuromorphic olfactionNeuromorphic olfaction combines sensing of chemical signals with brain-inspired circuit architectures to emulate key computational principles of biological olfactory systems. This approach holds strong promises for real-life applications, including detection of dangerous compounds, air-quality monitoring, and health diagnostics. However, real-world deployment remains constrained by critical limitations: lack of robust few-shot learning and class-incremental continual learning algorithms, particularly under the constraints set by the sensing and processing hardware. Here, we introduce Spi-Fly, a spiking neural network architecture inspired by the olfactory circuit of Drosophila. Spi-Fly combines high-dimensional sparse coding with an associative memory mechanism, enabling rapid few-shot learning, stable class-incremental continual learning without backpropagation, and operates effectively under low-bit precision. Our results suggest that fruit fly-inspired sparse associative learning provides a hardware-ready pathway toward fast, continual, and energy-efficient neuromorphic olfactory intelligence.
- The following article is Open accessExtreme-environment-resilient MoWS2/HfOx heterojunction photonic memristor crossbar arrays for neuromorphic computing
Abdul Momin Syed et al 2026 Neuromorph. Comput. Eng. 6 031001
View article, Extreme-environment-resilient MoWS2/HfOx heterojunction photonic memristor crossbar arrays for neuromorphic computingPDF, Extreme-environment-resilient MoWS2/HfOx heterojunction photonic memristor crossbar arrays for neuromorphic computingWe report environmentally robust optoelectronic memristive devices based on an ITO/MoWS2/HfOx/Pt heterostructure for neuromorphic computing applications. Individual dot-point devices exhibit stable bipolar resistive switching with an ON/OFF ratio of ∼1k and retention exceeding 10k s, alongside broadband, photo-tunable responsivity across the visible spectrum (405–785 nm), enabling wavelength-dependent synaptic modulation. To address scalability and device performance, 10 µm2 crossbar arrays were developed, demonstrating endurance beyond 100k cycles and reliable operation under harsh conditions, including temperatures up to 200 °C and aqueous environments. Notably, the proposed crossbar platform combines high-temperature operation, direct water-exposure resilience, broadband optoelectronic functionality, and neuromorphic behavior within a single heterojunction architecture. The crossbar array devices show intrinsic time-dependent photoresponse decay that follows a single-exponential relaxation, providing a hardware-level analogue of synaptic forgetting. Based on these characteristics, a binary neural network simulation for image-diminishing tasks achieves a classification accuracy of 91.76%. These results establish the MoWS2/HfOx heterostructure as a promising platform for resilient, multifunctional, and time-adaptive neuromorphic hardware.
- The following article is Open accessMore than MACs: exploring the role of neuromorphic engineering in the age of LLMs
Wilkie Olin-Ammentorp 2026 Neuromorph. Comput. Eng. 6 012002
View article, More than MACs: exploring the role of neuromorphic engineering in the age of LLMsPDF, More than MACs: exploring the role of neuromorphic engineering in the age of LLMsThe introduction of large language models has significantly expanded global demand for computing; addressing this growing demand requires novel approaches that introduce new capabilities while addressing extant needs. Although inspiration from biological systems served as the foundation on which modern artificial intelligence (AI) was developed, many modern advances have been made without clear parallels to biological computing. As a result, the ability of techniques inspired by ‘natural intelligence’ (NI) to inflect modern AI systems may be questioned. However, by analyzing remaining disparities between AI and NI, we argue that further biological inspiration can contribute towards expanding the capabilities of artificial systems, enabling them to succeed in real-world environments and adapt to niche applications. To elucidate which NI mechanisms can contribute toward this goal, we review and compare elements of biological and artificial computing systems, emphasizing areas of NI that have not yet been effectively captured by AI. We then suggest areas of opportunity for NI-inspired mechanisms that can inflect AI hardware and software.
- The following article is Open accessNoise-Robust conceptors for physical reservoir computing: adaptation to perturbations
Gemma Infantes-Llinares et al 2026 Neuromorph. Comput. Eng. 6 034012
View article, Noise-Robust conceptors for physical reservoir computing: adaptation to perturbationsPDF, Noise-Robust conceptors for physical reservoir computing: adaptation to perturbationsConceptors are a powerful extension of reservoir computing (RC) that enable the selective recall and stabilization of internal dynamics. However, their application to physical RC remains challenging because measured reservoir states are inevitably affected by noise and physical perturbations. In this work, we propose a noise-robust cross-trial-correlation-based (CTC) method for computing conceptors in noisy reservoir systems. By exploiting the consistency of the reservoir response across repeated trials, the method suppresses noise contributions that are uncorrelated between measurements. Numerical simulations of leaky echo state networks under additive state noise and parameter drift show that CTC-based conceptors preserve the relevant internal dynamics and extend the operational range of the reservoir compared with standard conceptors and unconstrained reservoirs. In an autonomous-generation task, the CTC-based conceptor maintains predictive capability beyond 50% noise, where the other configurations fail to sustain autonomous generation. Under combined noise and parameter drift, the CTC approach maintains normalized root mean square error values below 0.3, while the alternative approaches considered exceed this error level in the tested conditions. These numerical results establish a concrete step towards adapting conceptor-based control to physical RC platforms.
- The following article is Open accessA neuromorphic digital Ising solver with Tabu-inspired inhibitory dynamics for scalable graph optimization
Juan Núñez and Rafaella Fiorelli 2026 Neuromorph. Comput. Eng. 6 034009
View article, A neuromorphic digital Ising solver with Tabu-inspired inhibitory dynamics for scalable graph optimizationPDF, A neuromorphic digital Ising solver with Tabu-inspired inhibitory dynamics for scalable graph optimizationWe present a fully digital Ising solver for maximum-cut implemented on a low-cost Artix-7 field-programmable gate array (FPGA), where tabu-inspired inhibitory dynamics are realized as a compact, Block RAM-resident short-term memory. The solver operates in deterministic fixed-point arithmetic and scales up to the on-chip limit of
spins across multiple graph sizes and sparsity regimes. We benchmark the proposed Tabu-based dynamics against (i) a parallel Hopfield-network update rule implemented on the same FPGA, and (ii) a CPU-based quantum approximate optimization algorithm (QAOA) reference used as a fixed variational baseline for solution quality under a prescribed budget. Across the tested graph families, the Tabu-enhanced solver reaches higher cut values with reduced run-to-run dispersion than purely deterministic descent. Quantitatively, field-aligned warm start improves the median normalized cut of TS by 0.014 and reduces solve time by ms at , . At the largest tested size (), TS improves the median normalized cut over the fixed-budget CPU-QAOA reference by 0.014–0.016, with median CPU–FPGA solve-time differences of 640–720 ms under the reported protocol. The FPGA implementation closes timing at 100 MHz, demonstrating that short-term inhibitory memory can be embedded in a fully digital Ising network without relying on stochasticity, analog variability, or annealing schedules.
- The following article is Open accessTouchReal: an online neuromorphic tactile framework for biomimetic afferent spike generation based on TouchSim
Xingchen Xu et al 2026 Neuromorph. Comput. Eng. 6 034017
View article, TouchReal: an online neuromorphic tactile framework for biomimetic afferent spike generation based on TouchSimPDF, TouchReal: an online neuromorphic tactile framework for biomimetic afferent spike generation based on TouchSimRobotic tactile sensors usually provide continuous, sensor-specific signals such as force, pressure, or vibration. Although such signals are useful for many perception tasks, they are not directly compatible with afferent-level neural representations used in biological touch or spike-based processing systems. Here, we present TouchReal, an online neuromorphic tactile framework that converts signals from a low-cost multimodal tactile sensor into biomimetic SA1-, RA-, and PC-like spike trains inspired by the neural simulator package TouchSim. The hardware combines a capacitive SingleTact force sensor for static contact information with a PVDF piezoelectric film for dynamic vibration-sensitive responses. Raw sensor signals are processed through a pre-processing pipeline and stateful leaky integrate-and-fire afferent models. The generated spike trains reproduce several classical temporal, frequency-dependent, and receptive-field-like response properties of cutaneous afferents at an average absolute latency of 130.02 ms with a 32 ms update interval. Functional verification further shows that SA1 and RA spikes support force regression, while PC spikes enable texture classification with around 90% accuracy using temporal encoding features. These results suggest that TouchReal provides an interpretable afferent-level tactile representation for biomimetic robotic sensing, opening up possibilities for neuroprosthetic feedback and robotic models of human perception.
- The following article is Open accessWhy temporal spike order reversal drops spiking network accuracy and how to partially mitigate it
Nhan Trong Luu et al 2026 Neuromorph. Comput. Eng. 6 034016
View article, Why temporal spike order reversal drops spiking network accuracy and how to partially mitigate itPDF, Why temporal spike order reversal drops spiking network accuracy and how to partially mitigate itSpiking neural networks (SNNs) offer an energy-efficient alternative to traditional neural networks by utilizing discrete, temporally precise spike events. However, this study identifies a critical vulnerability in SNNs on recently established bit-based codes: consistent performance degradation when temporal spike encoding orders are reversed, such as using least-significant-bit ordering instead of most-significant-bit. We theoretically formalize this phenomenon as premature state annihilation, wherein early noisy spikes in information-discordant encodings trigger hard resets in leaky integrate-and-fire (LIF) neurons. These resets erase accumulated membrane state and, because the effective temporal influence of an input is largest for early timesteps, leave the backpropagated learning signal concentrated where the information is not. We measure the per-timestep class-mutual-information profile of six encodings directly, without reference to network accuracy, and show that the resulting concordance ordering predicts the observed degradation. While dense codes like weighted phase encoding suffer catastrophic drops (up to
), sparse codes like time-to-first-spike remain robust, and exchangeable rate codes are provably invariant to reversal. We evaluate several mitigation strategies, finding that parametric LIF (PLIF) neurons and aggressive membrane leakage significantly recover performance by adapting to or suppressing early noise. - The following article is Open accessFew-shot, continual learning for spiking neuromorphic olfaction
Kevin Max and Yang Shen 2026 Neuromorph. Comput. Eng. 6 034013
View article, Few-shot, continual learning for spiking neuromorphic olfactionPDF, Few-shot, continual learning for spiking neuromorphic olfactionNeuromorphic olfaction combines sensing of chemical signals with brain-inspired circuit architectures to emulate key computational principles of biological olfactory systems. This approach holds strong promises for real-life applications, including detection of dangerous compounds, air-quality monitoring, and health diagnostics. However, real-world deployment remains constrained by critical limitations: lack of robust few-shot learning and class-incremental continual learning algorithms, particularly under the constraints set by the sensing and processing hardware. Here, we introduce Spi-Fly, a spiking neural network architecture inspired by the olfactory circuit of Drosophila. Spi-Fly combines high-dimensional sparse coding with an associative memory mechanism, enabling rapid few-shot learning, stable class-incremental continual learning without backpropagation, and operates effectively under low-bit precision. Our results suggest that fruit fly-inspired sparse associative learning provides a hardware-ready pathway toward fast, continual, and energy-efficient neuromorphic olfactory intelligence.
- The following article is Open accessBio-inspired minimal hardware implementation of spike-time dependent plasticity for intelligent spiking neural networks
Adrien d’Hollande et al 2026 Neuromorph. Comput. Eng. 6 034015
View article, Bio-inspired minimal hardware implementation of spike-time dependent plasticity for intelligent spiking neural networksPDF, Bio-inspired minimal hardware implementation of spike-time dependent plasticity for intelligent spiking neural networksWe introduce a hardware circuit model that implements spike-time dependent plasticity (STDP) to endow spiking neural networks with learning capabilities. Our circuit model is characterized as both minimal and bio-inspired, due to its simplicity and to a novel active dendrite compartment that mimics the synaptic potentiation mechanism. The active dendrite consists of an integrate-and-fire stage which produces a train of pulses whose number is inversely related to the timing between pre- and post-synaptic spikes. The dendrite pulses modulate in a reliable manner the synaptic efficacy (conductance) that we implemented with a digipot, considered as an idealized non-volatile memristor. We demonstrate the behavior of the circuit by implementing a minimal spiking neuron model of associative learning by STDP, which is analog to the classic conditioning experiment of Pavlov’s dog.
- The following article is Open accessBiologically inspired memristive neuron capable of on-chip learning
Nadia Jimenez Olalla et al 2026 Neuromorph. Comput. Eng. 6 034014
View article, Biologically inspired memristive neuron capable of on-chip learningPDF, Biologically inspired memristive neuron capable of on-chip learningThe brain embeds learning algorithms within its physical architecture, enabling on-site learning processes with remarkable advantages such as energy efficiency, learning autonomy and continual learning capabilities. Current memristive neuromorphic implementations, despite being inspired by the brain, are predominantly trained via offline, software-based methods. Consequently, this paradigm restricts their potential to realize on-chip learning. To address this limitation, we implement a simple memristive-based electronic circuit with an op-amp that emulates a neuron with biologically inspired learning rules, characterized by recent electrophysiological observations. To demonstrate its potential as a fundamental computational primitive, we integrate it into a network with one hidden layer capable of learning all fundamental binary operations. As a proof-of-concept, we build a physical circuit that successfully learns and performs XOR, AND, and OR logic operations. To validate the scalability of our approach beyond simple logic, we also perform SPICE simulations on a compressed MNIST classification task. Therefore, the proposed circuit could be leveraged to build memristive neuromorphic systems capable of doing on-chip learning.
- The following article is Open accessA preliminary exploration of the differences and conjunction of traditional and brain-inspired navigation
Xu He et al 2026 Neuromorph. Comput. Eng. 6 032001
View article, A preliminary exploration of the differences and conjunction of traditional and brain-inspired navigationPDF, A preliminary exploration of the differences and conjunction of traditional and brain-inspired navigationDeveloping universal positioning, navigation, and timing (PNT) remains an enduring pursuit. Today’s complex environments call for PNT systems that are more resilient, energy-efficient, and cognitively capable as human beings. As a conceptual and preliminary exploration, this paper tentatively explores how unmanned systems could potentially integrate brain-inspired spatial cognition with the high precision of traditional navigation. We offer an exploratory perspective and preliminary roadmap for the envisioned transition of PNT from ‘tool-oriented’ to ‘cognition-driven’ paradigms. Our exploratory contributions encompass: (1) a multi-level analysis of differences among traditional navigation, biological brain navigation, and brain-inspired navigation (BIN); (2) a preliminary fusion framework that integrates key elements of traditional and BIN approaches; and (3) forward-looking recommendations for the future development of BIN. This work does not purport to present a complete, experimentally validated navigation system. Additional resources can be available at: https://github.com/BINUCOE/Exploration_for_Conjunction_Different_PNT.
- The following article is Open accessA review of event-based vision sensor fusion: architectures, evaluation and robustness challenges
Anusha Devulapally et al 2026 Neuromorph. Comput. Eng. 6 022003
View article, A review of event-based vision sensor fusion: architectures, evaluation and robustness challengesPDF, A review of event-based vision sensor fusion: architectures, evaluation and robustness challengesEvent-based vision is a neuromorphic sensing approach that enables low-latency, energy-aware perception by encoding brightness changes as sparse, asynchronous events rather than dense image frames. Event cameras provide microsecond-level timestamps and high dynamic range, supporting perception during fast motion and challenging illumination. In autonomy, event streams are often fused with complementary sensors such as inertial measurement units, color cameras, light-detection-and-ranging sensors, or radar to improve scale estimation, robustness, and redundancy. Event-centric fusion is challenging because sensor clocks and noise models differ across modalities, event rates are activity-dependent, event representations trade timing fidelity for computational convenience, and hardware cost is often dominated by communication and memory movement. Robustness to missing or degraded modalities is common in deployment but remains inconsistently evaluated. This topical review synthesizes event-based vision fusion around three coupled design decisions: fusion stage, temporal coupling, and event representation. We show how these choices determine whether systems preserve event-driven efficiency or revert to dense processing. As a case study, we review event-based depth estimation, consolidate benchmark results, and analyze missing-modality behavior. The evidence suggests that many gains are reported primarily as accuracy improvements, with limited analysis of modality dropout, event-rate shifts, timing mismatch, preprocessing cost, and efficiency. We relate recurring patterns to optical flow and semantic perception, connect them to neuromorphic hardware and hardware-algorithm co-design, and conclude with benchmarking recommendations and open problems in robustness, scalability, and training of spiking and hybrid models.
- The following article is Open accessDefect dynamics in 2D van der Waals materials for hardware security
Shiquan Yan et al 2026 Neuromorph. Comput. Eng. 6 022002
View article, Defect dynamics in 2D van der Waals materials for hardware securityPDF, Defect dynamics in 2D van der Waals materials for hardware securityThe accelerated progression of artificial intelligence and the Internet of Things has resulted in a substantial increase in demand for hardware-based security solutions, particularly for resource-constrained edge applications. Achieving the security mainly depends on the unpredictability of cryptographic keys, which are fundamentally generated by hardware security primitives, such as true random number generators (TRNGs) and physically unclonable functions (PUFs). However, these hardware security solutions currently rely on complementary metal-oxide-semiconductor processes, which are increasingly constrained by scaling limits and power inefficiencies. Two dimensional van der Waals (2D vdW) materials have been identified as a promising platform due to their atomic thickness, energy efficiency, and inherent stochastic behavior, which originates from defect dynamics processes. This review focuses on microscopic origins of randomness in 2D vdW materials, including electron trapping/detrapping and ion migration, that underlie phenomena such as random telegraph noise and variability in resistance switching. These stochastic phenomena are then exploited to implement TRNGs and PUFs. Recent research progress in the application of these hardware security primitives based on 2D vdW materials, including authentication, secure communications, image encryption, and privacy-preserving computing, is summarized. Challenges in this field and future research directions are also discussed.
- The following article is Open accessNeuromorphic computing for radar and radio systems: a survey
Hanna Hamrell et al 2026 Neuromorph. Comput. Eng. 6 022001
View article, Neuromorphic computing for radar and radio systems: a surveyPDF, Neuromorphic computing for radar and radio systems: a surveyTaking inspiration from the brain on how to create energy efficient and low latency neuromorphic systems has the potential to create new opportunities with AI across many domains. Firstly, it creates a possibility to mitigate problems with too large digital signal processing costs in various technologies. Secondly, it also enables the use of AI and machine learning algorithms where it is currently impossible due to energy constraints. Recently, neuromorphic technology has been introduced to radio communication and radar applications. In this work, we highlight advantages of applying energy efficient, low latency and often lightweight neuromorphic computing for radar and radio signal processing. We perform a comprehensive review of the main current works on neuromorphic technology for radar applications, focusing on frequency-modulated continuous-wave and synthetic aperture radar. Additionally, we cover radio frequency signal classification for both radar and radio signals. Our ambition is to facilitate research on neuromorphic computing for radar and radio systems, as well as help bringing researchers from these fields together.
- The following article is Open access2D-materials for analog in-memory computing: a device-centric review of advantages and limitations
Jimin Shim et al 2026 Neuromorph. Comput. Eng. 6 012003
View article, 2D-materials for analog in-memory computing: a device-centric review of advantages and limitationsPDF, 2D-materials for analog in-memory computing: a device-centric review of advantages and limitationsThis review examines the practical advantages of two-dimensional materials for energy-efficient in-memory computing by assembling a curated, experiment-only dataset covering 32 material systems across diverse device structures, mechanisms, and fabrication routes. Energy analysis was standardized using an averaged pulse-based metric, and key figures of merit—switching energy, on/off ratio, endurance, retention, and linearity—were compared against structural and mechanistic factors. Two low-energy-consumption design pathways emerge: ultrathin (<10 nm) two-terminal devices exploiting filament formation for sub-μs updates and three-terminal heterojunction devices leveraging charge trapping to achieve nA-level programming currents over longer timescales. However, dynamic on/off ratios remain modest and are often overstated by DC sweep data. Endurance improves with shorter switching times, and the most intrinsically linear conductance evolution is observed in three-terminal gate-controlled devices employing charge trapping, Schottky barrier modulation, or ion intercalation. No universal optimum exists, as enhancing one performance metric typically compromises another. Based on the comparative analysis presented in this review, three near-term levers emerge as particularly relevant for translating selective material advantages into reproducible system-level gains: standardized pulsed benchmarking, scalable chemical vapor deposition growth with controlled defects and interfaces, and device–circuit co-design.
- The following article is Open accessThermodynamic computing with oscillatory neural networks for linear algebra problems
Tsormpatzoglou et al
View accepted manuscript, Thermodynamic computing with oscillatory neural networks for linear algebra problemsPDF, Thermodynamic computing with oscillatory neural networks for linear algebra problemsPhysical computing paradigms have recently gained considerable traction. By letting physics take care of the computation, these paradigms offer an energy-efficient alternative to conventional von Neumann architectures. Among these approaches, oscillatory neural networks (ONNs) have emerged as promising candidates, primarily explored as Ising machines for combinatorial optimization and as analog counterparts to Hopfield networks for associative memory. In this work, we investigate a new computational role for ONNs and explore their feasibility in solving linear algebra problems, specifically matrix inversion and linear systems of equations. Inspired by thermodynamic principles, we analytically show that the linear approximation of the coupled Kuramoto oscillator model enables these problems to be mapped onto ONNs. We validate our theoretical framework with numerical simulations and identify parameter regimes for which the ONN yields the highest accuracy. We also provide time-to-solution estimates to assess computational feasibility. These results reveal a previously unexplored application domain for ONNs, going beyond combinatorial optimization and memory tasks and highlighting their potential as a physical solver for linear algebra.
- The following article is Open accessNode perturbation can effectively train multi-layer neural networks
Dalm et al
View accepted manuscript, Node perturbation can effectively train multi-layer neural networksPDF, Node perturbation can effectively train multi-layer neural networksBackpropagation (BP) remains the dominant and most successful method for training parameters of deep neural network models. However, BP relies on two computationally distinct phases, does not provide a satisfactory explanation of biological learning, and can be challenging to apply for training of networks with discontinuities or noisy node dynamics. By comparison, node perturbation (NP), also known as activity-perturbed forward gradients, proposes learning by the injection of noise into network activations, and subsequent measurement of the induced loss change. NP relies on two forward (inference) passes, does not make use of network derivatives, and has been proposed as a model for learning in biological systems. However, standard NP is highly data inefficient and can be unstable due to its unguided noise-based search process. In this work, we develop a modern perspective on NP by relating it to the directional derivative and incorporating input decorrelation. We find that a closer alignment with directional derivatives together with input decorrelation at every layer theoretically and practically enhances performance of NP learning with large improvements in parameter convergence and much higher performance on the test data, approaching that of BP. Furthermore, our novel formulation allows for application to noisy systems in which the noise process itself is inaccessible, which is of particular interest for on-chip learning in neuromorphic systems.
- The following article is Open accessAn infrared-sensing memory device based on Se0.3Te0.7 /CuInP2S6 heterostructure for convolutional neural network computing
Zheng et al
View accepted manuscript, An infrared-sensing memory device based on Se0.3Te0.7 /CuInP2S6 heterostructure for convolutional neural network computingPDF, An infrared-sensing memory device based on Se0.3Te0.7 /CuInP2S6 heterostructure for convolutional neural network computingThe advent of the big data and the Internet of Things (IoT) has created an urgent demand for novel devices capable of simultaneously realizing in-sensor and in-memory computing. Although the introduction of van der Waals (vdW) materials has provided corresponding solutions, their applications in in-sensor computing operating at the infrared (IR) band remains less explored. In this work, we developed an infrared-sensing memory device (ISMD) based on Se0.3Te0.7/CuInP2S6 (CIPS) vdW heterostructure, which combines Se0.3Te0.7 semiconductor with considerable infrared (IR) photoresponse as the channel and CIPS as the ferroelectric layer. Leveraging plasma-induced interfacial charge trapping as the dominant mechanism, which is further stabilized by the ferroelectric polarization effect of CIPS, the device exhibits multi-bit non-volatile storage characteristics under electrical control. In addition, benefiting from the superior IR photoresponse of Se0.3Te0.7, the device demonstrates an instantaneous response to 1550 nm infrared light, with the responsivity controllably modulated by electrically tuning the channel conductance state. We further simulated a convolutional neural network (CNN) system based on ISMD. The frontend of the architecture utilizes the optoelectronic properties of ISMD as convolution kernel parameters, enabling selective responses to edges in different directions. The backend is a fully connected classifier constrained by actual conductance values. Using this system, we perform handwritten digit classification on the Modified National Institute of Standards and Technology (MNIST) dataset, achieving an accuracy of over 90%. The ISMD provides new materials and structural options for preparing memory devices capable of sensing IR bands and offers a new paradigm for realizing integrated in-sensor and in-memory computing.
- The following article is Open accessMoisture effects on diffusive memristors
Kim et al
View accepted manuscript, Moisture effects on diffusive memristorsPDF, Moisture effects on diffusive memristorsBiological nervous systems encode information through transient, event-driven spikes, motivating neuromorphic hardware that can reproduce such dynamics efficiently. Diffusive memristors are strong candidates because their volatile, threshold-driven responses generate spike-like signals and support temporal processing. However, their switching relies on ionic motion and transient metal clusters that are highly sensitive to interfacial chemistry, leaving the influence of environmental factors unresolved. Here, the chemical role of moisture in enabling volatile threshold switching is systematically established in symmetric Pt/Ag/SiO2/Ag/Pt diffusive memristors using a rigorously controlled fabrication and measurement framework. Systematic comparisons show that interfacial water facilitates Ag oxidation and hydrated transport pathways, whereas its depletion suppresses switching or increases variability. These findings demonstrate that moisture is not a minor perturbation but a fundamental chemical requirement for stable operation in such device systems. Controlling interfacial hydration emerges as a key design principle for achieving reliable and commercially scalable diffusive memristors for neuromorphic hardware.
- The following article is Open accessMetastable neural assemblies on a wiring–weight continuum
Schmitt et al
View accepted manuscript, Metastable neural assemblies on a wiring–weight continuumPDF, Metastable neural assemblies on a wiring–weight continuumNeural population activity typically evolves on low-dimensional manifolds and can be described as trajectories through quasi-stable assembly states. Here we develop a unified definition of clustered neural networks with local excitatory–inhibitory balance in which enhanced within-cluster effective coupling is implemented through connection probability (structural clustering), synaptic efficacy (weight clustering), or any mixture of both. We introduce a single mixing parameter κ ∈ [0, 1] that redistributes a defined cluster contrast between connection probabilities and synaptic efficacies while preserving the mean input of the underlying balanced random network. Mean-field theory and binary-network simulations show that metastable dynamics are supported across the full κ continuum. Varying κ changes higher-order input structure, reshaping multistable regimes, correlation structure, and the balance between single- and multi-cluster episodes. Because real nervous systems jointly organize topology and synaptic strength, our approach provides a biologically interpretable parametrization of clustered assembly models and a basis for future models combining structural and functional plasticity. We further demonstrate metastable switching in spiking leaky integrate-and-fire networks and in a BrainScaleS-2 neuromorphic implementation for the cases of structural, weight, and combined clustering. The $\kappa$-framework offers a controlled translation axis for neuromorphic and other constrained substrates, exposing trade-offs between routed synapse count, fan-in, synaptic weight resolution, and calibration when implementing attractor-based computational primiti
Trending on Altmetric
- The following article is Open access2022 roadmap on neuromorphic computing and engineering
Dennis V Christensen et al 2022 Neuromorph. Comput. Eng. 2 022501
View article, 2022 roadmap on neuromorphic computing and engineeringPDF, 2022 roadmap on neuromorphic computing and engineeringModern computation based on von Neumann architecture is now a mature cutting-edge science. In the von Neumann architecture, processing and memory units are implemented as separate blocks interchanging data intensively and continuously. This data transfer is responsible for a large part of the power consumption. The next generation computer technology is expected to solve problems at the exascale with 1018 calculations each second. Even though these future computers will be incredibly powerful, if they are based on von Neumann type architectures, they will consume between 20 and 30 megawatts of power and will not have intrinsic physically built-in capabilities to learn or deal with complex data as our brain does. These needs can be addressed by neuromorphic computing systems which are inspired by the biological concepts of the human brain. This new generation of computers has the potential to be used for the storage and processing of large amounts of digital information with much lower power consumption than conventional processors. Among their potential future applications, an important niche is moving the control from data centers to edge devices. The aim of this roadmap is to present a snapshot of the present state of neuromorphic technology and provide an opinion on the challenges and opportunities that the future holds in the major areas of neuromorphic technology, namely materials, devices, neuromorphic circuits, neuromorphic algorithms, applications, and ethics. The roadmap is a collection of perspectives where leading researchers in the neuromorphic community provide their own view about the current state and the future challenges for each research area. We hope that this roadmap will be a useful resource by providing a concise yet comprehensive introduction to readers outside this field, for those who are just entering the field, as well as providing future perspectives for those who are well established in the neuromorphic computing community.
- The following article is Open accessHands-on reservoir computing: a tutorial for practical implementation
Matteo Cucchi et al 2022 Neuromorph. Comput. Eng. 2 032002
View article, Hands-on reservoir computing: a tutorial for practical implementationPDF, Hands-on reservoir computing: a tutorial for practical implementationThis manuscript serves a specific purpose: to give readers from fields such as material science, chemistry, or electronics an overview of implementing a reservoir computing (RC) experiment with her/his material system. Introductory literature on the topic is rare and the vast majority of reviews puts forth the basics of RC taking for granted concepts that may be nontrivial to someone unfamiliar with the machine learning field (see for example reference Lukoševičius (2012 Neural Networks: Tricks of the Trade (Berlin: Springer) pp 659–686). This is unfortunate considering the large pool of material systems that show nonlinear behavior and short-term memory that may be harnessed to design novel computational paradigms. RC offers a framework for computing with material systems that circumvents typical problems that arise when implementing traditional, fully fledged feedforward neural networks on hardware, such as minimal device-to-device variability and control over each unit/neuron and connection. Instead, one can use a random, untrained reservoir where only the output layer is optimized, for example, with linear regression. In the following, we will highlight the potential of RC for hardware-based neural networks, the advantages over more traditional approaches, and the obstacles to overcome for their implementation. Preparing a high-dimensional nonlinear system as a well-performing reservoir for a specific task is not as easy as it seems at first sight. We hope this tutorial will lower the barrier for scientists attempting to exploit their nonlinear systems for computational tasks typically carried out in the fields of machine learning and artificial intelligence. A simulation tool to accompany this paper is available online7.
- The following article is Open accessHfO2-based resistive switching memory devices for neuromorphic computing
S Brivio et al 2022 Neuromorph. Comput. Eng. 2 042001
View article, HfO2-based resistive switching memory devices for neuromorphic computingPDF, HfO2-based resistive switching memory devices for neuromorphic computingHfO2-based resistive switching memory (RRAM) combines several outstanding properties, such as high scalability, fast switching speed, low power, compatibility with complementary metal-oxide-semiconductor technology, with possible high-density or three-dimensional integration. Therefore, today, HfO2 RRAMs have attracted a strong interest for applications in neuromorphic engineering, in particular for the development of artificial synapses in neural networks. This review provides an overview of the structure, the properties and the applications of HfO2-based RRAM in neuromorphic computing. Both widely investigated applications of nonvolatile devices and pioneering works about volatile devices are reviewed. The RRAM device is first introduced, describing the switching mechanisms associated to filamentary path of HfO2 defects such as oxygen vacancies. The RRAM programming algorithms are described for high-precision multilevel operation, analog weight update in synaptic applications and for exploiting the resistance dynamics of volatile devices. Finally, the neuromorphic applications are presented, illustrating both artificial neural networks with supervised training and with multilevel, binary or stochastic weights. Spiking neural networks are then presented for applications ranging from unsupervised training to spatio-temporal recognition. From this overview, HfO2-based RRAM appears as a mature technology for a broad range of neuromorphic computing systems.
- The following article is Open accessDYNAP-SE2: a scalable multi-core dynamic neuromorphic asynchronous spiking neural network processor
Ole Richter et al 2024 Neuromorph. Comput. Eng. 4 014003
View article, DYNAP-SE2: a scalable multi-core dynamic neuromorphic asynchronous spiking neural network processorPDF, DYNAP-SE2: a scalable multi-core dynamic neuromorphic asynchronous spiking neural network processorWith the remarkable progress that technology has made, the need for processing data near the sensors at the edge has increased dramatically. The electronic systems used in these applications must process data continuously, in real-time, and extract relevant information using the smallest possible energy budgets. A promising approach for implementing always-on processing of sensory signals that supports on-demand, sparse, and edge-computing is to take inspiration from biological nervous system. Following this approach, we present a brain-inspired platform for prototyping real-time event-based spiking neural networks. The system proposed supports the direct emulation of dynamic and realistic neural processing phenomena such as short-term plasticity, NMDA gating, AMPA diffusion, homeostasis, spike frequency adaptation, conductance-based dendritic compartments and spike transmission delays. The analog circuits that implement such primitives are paired with a low latency asynchronous digital circuits for routing and mapping events. This asynchronous infrastructure enables the definition of different network architectures, and provides direct event-based interfaces to convert and encode data from event-based and continuous-signal sensors. Here we describe the overall system architecture, we characterize the mixed signal analog-digital circuits that emulate neural dynamics, demonstrate their features with experimental measurements, and present a low- and high-level software ecosystem that can be used for configuring the system. The flexibility to emulate different biologically plausible neural networks, and the chip’s ability to monitor both population and single neuron signals in real-time, allow to develop and validate complex models of neural processing for both basic research and edge-computing applications.
- The following article is Open accessRecent progress in optoelectronic memristors for neuromorphic and in-memory computation
Maria Elias Pereira et al 2023 Neuromorph. Comput. Eng. 3 022002
View article, Recent progress in optoelectronic memristors for neuromorphic and in-memory computationPDF, Recent progress in optoelectronic memristors for neuromorphic and in-memory computationNeuromorphic computing has been gaining momentum for the past decades and has been appointed as the replacer of the outworn technology in conventional computing systems. Artificial neural networks (ANNs) can be composed by memristor crossbars in hardware and perform in-memory computing and storage, in a power, cost and area efficient way. In optoelectronic memristors (OEMs), resistive switching (RS) can be controlled by both optical and electronic signals. Using light as synaptic weigh modulator provides a high-speed non-destructive method, not dependent on electrical wires, that solves crosstalk issues. In particular, in artificial visual systems, OEMs can act as the artificial retina and combine optical sensing and high-level image processing. Therefore, several efforts have been made by the scientific community into developing OEMs that can meet the demands of each specific application. In this review, the recent advances in inorganic OEMs are summarized and discussed. The engineering of the device structure provides the means to manipulate RS performance and, thus, a comprehensive analysis is performed regarding the already proposed memristor materials structure and their specific characteristics. Moreover, their potential applications in logic gates, ANNs and, in more detail, on artificial visual systems are also assessed, taking into account the figures of merit described so far.
- The following article is Open accessFerroelectric-based synapses and neurons for neuromorphic computing
Erika Covi et al 2022 Neuromorph. Comput. Eng. 2 012002
View article, Ferroelectric-based synapses and neurons for neuromorphic computingPDF, Ferroelectric-based synapses and neurons for neuromorphic computingThe shift towards a distributed computing paradigm, where multiple systems acquire and elaborate data in real-time, leads to challenges that must be met. In particular, it is becoming increasingly essential to compute on the edge of the network, close to the sensor collecting data. The requirements of a system operating on the edge are very tight: power efficiency, low area occupation, fast response times, and on-line learning. Brain-inspired architectures such as spiking neural networks (SNNs) use artificial neurons and synapses that simultaneously perform low-latency computation and internal-state storage with very low power consumption. Still, they mainly rely on standard complementary metal-oxide-semiconductor (CMOS) technologies, making SNNs unfit to meet the aforementioned constraints. Recently, emerging technologies such as memristive devices have been investigated to flank CMOS technology and overcome edge computing systems’ power and memory constraints. In this review, we will focus on ferroelectric technology. Thanks to its CMOS-compatible fabrication process and extreme energy efficiency, ferroelectric devices are rapidly affirming themselves as one of the most promising technologies for neuromorphic computing. Therefore, we will discuss their role in emulating neural and synaptic behaviors in an area and power-efficient way.
- The following article is Open accessBeyond classification: directly training spiking neural networks for semantic segmentation
Youngeun Kim et al 2022 Neuromorph. Comput. Eng. 2 044015
View article, Beyond classification: directly training spiking neural networks for semantic segmentationPDF, Beyond classification: directly training spiking neural networks for semantic segmentationSpiking neural networks (SNNs) have recently emerged as the low-power alternative to artificial neural networks (ANNs) because of their sparse, asynchronous, and binary event-driven processing. Due to their energy efficiency, SNNs have a high possibility of being deployed for real-world, resource-constrained systems such as autonomous vehicles and drones. However, owing to their non-differentiable and complex neuronal dynamics, most previous SNN optimization methods have been limited to image recognition. In this paper, we explore the SNN applications beyond classification and present semantic segmentation networks configured with spiking neurons. Specifically, we first investigate two representative SNN optimization techniques for recognition tasks (i.e., ANN-SNN conversion and surrogate gradient learning) on semantic segmentation datasets. We observe that, when converted from ANNs, SNNs suffer from high latency and low performance due to the spatial variance of features. Therefore, we directly train networks with surrogate gradient learning, resulting in lower latency and higher performance than ANN-SNN conversion. Moreover, we redesign two fundamental ANN segmentation architectures (i.e., Fully Convolutional Networks and DeepLab) for the SNN domain. We conduct experiments on three semantic segmentation benchmarks including PASCAL VOC2012 dataset, DDD17 event-based dataset, and synthetic segmentation dataset combined CIFAR10 and MNIST datasets. In addition to showing the feasibility of SNNs for semantic segmentation, we show that SNNs can be more robust and energy-efficient compared to their ANN counterparts in this domain.
- The following article is Open accessReducing reservoir computer hyperparameter dependence by external timescale tailoring
Lina Jaurigue and Kathy Lüdge 2024 Neuromorph. Comput. Eng. 4 014001
View article, Reducing reservoir computer hyperparameter dependence by external timescale tailoringPDF, Reducing reservoir computer hyperparameter dependence by external timescale tailoringTask specific hyperparameter tuning in reservoir computing is an open issue, and is of particular relevance for hardware implemented reservoirs. We investigate the influence of directly including externally controllable task specific timescales on the performance and hyperparameter sensitivity of reservoir computing approaches. We show that the need for hyperparameter optimisation can be reduced if timescales of the reservoir are tailored to the specific task. Our results are mainly relevant for temporal tasks requiring memory of past inputs, for example chaotic timeseries prediction. We consider various methods of including task specific timescales in the reservoir computing approach and demonstrate the universality of our message by looking at both time-multiplexed and spatially-multiplexed reservoir computing.
- The following article is Open access2D materials and van der Waals heterojunctions for neuromorphic computing
Zirui Zhang et al 2022 Neuromorph. Comput. Eng. 2 032004
View article, 2D materials and van der Waals heterojunctions for neuromorphic computingPDF, 2D materials and van der Waals heterojunctions for neuromorphic computingNeuromorphic computing systems employing artificial synapses and neurons are expected to overcome the limitations of the present von Neumann computing architecture in terms of efficiency and bandwidth limits. Traditional neuromorphic devices have used 3D bulk materials, and thus, the resulting device size is difficult to be further scaled down for high density integration, which is required for highly integrated parallel computing. The emergence of two-dimensional (2D) materials offers a promising solution, as evidenced by the surge of reported 2D materials functioning as neuromorphic devices for next-generation computing. In this review, we summarize the 2D materials and their heterostructures to be used for neuromorphic computing devices, which could be classified by the working mechanism and device geometry. Then, we survey neuromorphic device arrays and their applications including artificial visual, tactile, and auditory functions. Finally, we discuss the current challenges of 2D materials to achieve practical neuromorphic devices, providing a perspective on the improved device performance, and integration level of the system. This will deepen our understanding of 2D materials and their heterojunctions and provide a guide to design highly performing memristors. At the same time, the challenges encountered in the industry are discussed, which provides a guide for the development direction of memristors.
- The following article is Open accessSpike-based local synaptic plasticity: a survey of computational models and neuromorphic circuits
Lyes Khacef et al 2023 Neuromorph. Comput. Eng. 3 042001
View article, Spike-based local synaptic plasticity: a survey of computational models and neuromorphic circuitsPDF, Spike-based local synaptic plasticity: a survey of computational models and neuromorphic circuitsUnderstanding how biological neural networks carry out learning using spike-based local plasticity mechanisms can lead to the development of real-time, energy-efficient, and adaptive neuromorphic processing systems. A large number of spike-based learning models have recently been proposed following different approaches. However, it is difficult to assess if these models can be easily implemented in neuromorphic hardware, and to compare their features and ease of implementation. To this end, in this survey, we provide an overview of representative brain-inspired synaptic plasticity models and mixed-signal complementary metal–oxide–semiconductor neuromorphic circuits within a unified framework. We review historical, experimental, and theoretical approaches to modeling synaptic plasticity, and we identify computational primitives that can support low-latency and low-power hardware implementations of spike-based learning rules. We provide a common definition of a locality principle based on pre- and postsynaptic neural signals, which we propose as an important requirement for physical implementations of synaptic plasticity circuits. Based on this principle, we compare the properties of these models within the same framework, and describe a set of mixed-signal electronic circuits that can be used to implement their computing principles, and to build efficient on-chip and online learning in neuromorphic processing systems.
Journal resources
Journal information
- 2021-present
Neuromorphic Computing and Engineering
doi: 10.1088/issn.2634-4386
Online ISSN: 2634-4386