Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

arXiv:2606.00818

A Retinomorphic Optical Spiking Neuron for Camouflaged Object Detection

Srilagna Sahoo, Adwaaiit Pande, Kartikey Thakar, Shubham Sahay, Saurabh Lodha

physics.app-phquant-phSubmitted May 30, 2026• Announced Jun 2, 2026
arXivHTMLPDF

Abstract

Advanced vision systems require retinomorphic, energy-efficient spike-based preprocessing of dynamic visual scenes. Here, we demonstrate multiple retinal preprocessing functionalities by leveraging a Hodgkin-Huxley-based optical spiking neuron (OSHN) that incorporates a two-dimensional anti-ambipolar phototransistor operated in the subthreshold regime to minimize power consumption. OSHN exhibits wavelength- and intensity-sensitive spike encoding with energy consumption per spike of 0.9 pJ under dark, 2 pJ at 480 nm (mid wavelength, M), and 24.5 pJ at 800 nm (long wavelength, L). The low (biological)-to-high spiking rate (0 - 2 kHz) with substantially faster response times (4.2 $μ$s - 1.25 ms) than the human retina (30 ms - 60 ms), reveal OSHN's fast decision-making capability. OSHN facilitates concurrent spectral-spatial processing by emulating retinal antagonistic center-surround receptive fields (CSRFs) at a single wavelength (480 nm or 800 nm) with varying intensities, visual adaptation (at 480 nm) to prevent system saturation, and L-M cone opponency in midget ganglion cells. Finally, a CSRF-augmented spiking neural network (SNN) has been developed for camouflaged object detection, achieving 4.4%, 10.4%, and 28.4% improvements in accuracy over conventional SNN on FMNIST, COD10K, and synthetic camouflaged datasets, outperforming existing photoactive spiking architectures while enabling event-driven intelligent edge vision systems.

Related papers

QDS-SNN: Energy-efficient Quantum Deeply-Supervised Spiking Neural Network Algorithm for Traffic Sign Recognition

Zhiguo Qu, Keqi Li, Le Sun +4 more

Traffic sign recognition is crucial for intelligent transportation and autonomous driving, as it can improve driving efficiency and ensure road safety. However, traditional recognition methods are based on large datasets and intensive computation, which limits their real-time applicability. Spiking Neural Networks (SNNs) offer a biologically inspired, energy-efficient alternative due to their spatiotemporal processing capabilities, but suffer from information loss and vanishing gradients during training. To overcome these limitations, this study proposes a Quantum Deep-supervised Spiking Neural Network (QDS-SNN) that integrates Quantum Neural Networks (QNNs) for efficient, low-power deep supervision. Using quantum superposition and entanglement, QNNs enable expressive representations and parallel computation, thereby enhancing performance without compromising energy efficiency. The proposed QDS-SNN incorporates a temporally and spatially adaptive LIF (TSA-LIF) neuron and a quantum-assisted classifier module (QACM) to mitigate gradient issues and improve training effectiveness. This study conducts experiments on the PennyLane quantum simulation platform, and the results show that QDS-SNN achieves 99.72\% accuracy on the GTSRB dataset in only 6 time steps -- outperforming the MS-ResNet baseline by 1.32\% while reducing energy consumption by 55.77\%. In the TSRD dataset, it achieves 97.90\% accuracy while reducing energy use to 52.68\% of the baseline. These results demonstrate that QDS-SNN offers a high-performance, energy-efficient solution for traffic sign recognition in intelligent transportation systems.

arXiv:2606.07657•Jun 3, 2026•0 citations

Parameter efficient hybrid spiking-quantum convolutional neural network with surrogate gradient and quantum data-reupload

Nhan Trong Luu, Duong Trung Luu, Nam Ngoc Pham +1 more

The rapid advancement of artificial intelligence (AI) and deep learning (DL) has catalyzed the emergence of several optimization-driven subfields, notably neuromorphic computing and quantum machine learning. Leveraging the differentiable nature of hybrid models, researchers have explored their potential to address complex problems through unified optimization strategies. One such development is the Spiking Quantum Neural Network (SQNN), which combines principles from spiking neural networks (SNNs) and quantum computing. However, existing SQNN implementations often depend on pretrained SNNs due to the non-differentiable nature of spiking activity and the limited scalability of current SNN encoders. In this work, we propose a novel architecture—Spiking-Quantum Data Re-upload Convolutional Neural Network (SQDR-CNN)—that enables joint training of convolutional SNNs and quantum circuits within a single backpropagation framework. Unlike its predecessor, SQDR-CNN allow convergence to reasonable performance without the reliance of pretrained spiking encoder and subsetting datasets. We also clarified some theoretical foundations, testing new design using quantum data-reupload with different training algorithm-initialization and evaluate the performance of the proposed model under noisy simulated quantum environments. As a result, we were able to achieve 86% of the mean top-performing accuracy of the state of the art (SOTA) SNN baselines, yet uses only 0.5% of the smallest spiking model’s parameters. Through this integration of neuromorphic and quantum paradigms, we aim to open new research directions and foster technological progress in multi-modal, learnable systems.

PeerJ Computer Science•Feb 24, 2026•4 citations

Quantum spiking neural networks for image classification

Shilong Liu, Yongjian Gu

As the field of artificial intelligence experiences the emergence of various large-scale models, the computing power requirements are increasing. Simultaneously, Moore’s Law is approaching its limits, which intensifies the need to address how to perform high-dimensional complex data computations efficiently and with minimal energy consumption. Quantum computing and neuromorphic computing, with their unique features, offer potential solutions to this contemporary challenge. In this study, we aim to integrate quantum computing with neuromorphic computing, and develop a quantum spiking neural networks architecture. We proposed three measurement strategy to reducing operational costs, making it more friendly to near-term quantum hardware. We evaluated the performance of these three models on the standard MNIST dataset for classification tasks and found that they maintained a high level of accuracy despite a reduced number of parameters and a substantial decrease in the number of quantum circuit shots.

International Conference on Algorithms, Network, and Communication Technology (ICANCT)•Mar 3, 2025•1 citation

Neuromorphic Quantum Computing: Integrated Bio-Inspired Spiking Networks with Room-Temperature Polarons and Non-Markovian Synaptic Plasticity

Yoko Hasebe

Abstract: Contemporary computational intelligence confronts a dual thermodynamic barrier: classical deep learning accelerators are throttled by the von Neumann memory-bus bottleneck and megawatt-scale power consumption, while gate-based quantum processors remain confined to multi-kilowatt cryogenic dilution refrigerators operating at millikelvin temperatures. In contrast, the biological human brain executes high-dimensional perceptual synthesis and continuous learning within a tight thermal envelope of approximately 20 W at physiological temperatures (T ≈ 310 K), leveraging event-driven sparse spiking dynamics and sub-cellular vibronic transport mechanisms. This monograph formalizes the theoretical foundations and solid-state circuit architecture for a Quantum Spiking Neural Network (QSNN) powered by room-temperature polarons and biomimetic phononics: (1) We model artificial quantum neurons using non-linear exciton-polarons in lithium niobate (LiNbO3) and diamond acoustic metamaterial waveguides, demonstrating threshold-driven coherent optical-acoustic pulse emission (< 100 ps) operating at ambient temperature (300 K); (2) We formulate a Non-Markovian Quantum Synaptic Plasticity Model, proving that structured vibronic phonon modes act as an intrinsic temporal memory kernel supporting quantum Spike-Timing-Dependent Plasticity (Q-STDP) with long-term retention (τ_ret > 10^3 s) without requiring cryogenic volatile refresh cycles; and (3) We derive the physical energy dissipation budget, proving that each quantum synaptic event consumes less than 1.8 fJ (femtojoules per spike)—three orders of magnitude below CMOS neuromorphic baselines. We establish non-equilibrium Bose-Hubbard Hamiltonians, synaptic update operators, and planar wafer-scale integration blueprints hosting 10^7 quantum neurons and 10^10 quantum synapses, establishing a non-von Neumann foundation for cryogen-free, brain-scale quantum cognitive computing.

•Oct 13, 2026•0 citations

Parameter efficient hybrid spiking-quantum convolutional neural network with surrogate gradient and quantum data-reupload

Nhan Trong Luu, Duong, Luu Trung, Pham Ngoc Nam +1 more

The rapid advancement of artificial intelligence (AI) and deep learning (DL) has catalyzed the emergence of several optimization-driven subfields, notably neuromorphic computing and quantum machine learning. Leveraging the differentiable nature of hybrid models, researchers have explored their potential to address complex problems through unified optimization strategies. One such development is the Spiking Quantum Neural Network (SQNN), which combines principles from spiking neural networks (SNNs) and quantum computing. However, existing SQNN implementations often depend on pretrained SNNs due to the non-differentiable nature of spiking activity and the limited scalability of current SNN encoders. In this work, we propose a novel architecture, Spiking-Quantum Data Re-upload Convolutional Neural Network (SQDR-CNN), that enables joint training of convolutional SNNs and quantum circuits within a single backpropagation framework. Unlike its predecessor, SQDR-CNN allow convergence to reasonable performance without the reliance of pretrained spiking encoder and subsetting datasets. We also clarified some theoretical foundations, testing new design using quantum data-reupload with different training algorithm-initialization and evaluate the performance of the proposed model under noisy simulated quantum environments. As a result, we were able to achieve 86% of the mean top-performing accuracy of the SOTA SNN baselines, yet uses only 0.5% of the smallest spiking model's parameters. Through this integration of neuromorphic and quantum paradigms, we aim to open new research directions and foster technological progress in multi-modal, learnable systems.

arXiv:2512.03895•Dec 3, 2025•0 citations

A hybrid spiking neural network - quantum framework for spatio-temporal data classification: a case study on EEG data

Ravi Kumar Jha, Nikola Kirilov Kasabov, Saugat Bhattacharyya +2 more

Abstract The study introduces a hybrid computational framework that combines neuro-inspired information processing using spiking neural networks (SNN) and quantum information processing using quantum kernels to develop quantum-enhanced machine learning models, demonstrated through the classification of EEG data as a case study. In the proposed SNN-quantum kernel classifier (SNN-QC), SNN with spike time information representation is employed to learn spatio-temporal interactions (EEG recorded from multiple channels over time). Frequency-based (rate-based) information as spike frequency state vectors are extracted from the SNN and classified using a quantum classifier. In the latter part, we use the quantum kernel approach utilizing feature maps for classification tasks. The proposed SNN-QC is demonstrated on a benchmark EEG dataset to classify three distinct wrist movement tasks in six binary classification setups as a proof of concept. We introduce a novel feature map with high-order nonlinearity, which has outperformed current state-of-the-art feature maps and various machine learning methods in most of the case studies. Furthermore, the role of hyperparameters for enhanced feature maps is also highlighted. The performance of SNN-QC is evaluated using statistical metrics and cross-validation techniques, demonstrating its 1 efficacy across multiple binary classifiers. An experimental validation is also performed on an IBM QPU. The results demonstrate that the SNN-QC significantly outperforms the models that use statistical features rather than features extracted from the SNN as SNN accounts for the temporal interaction between the spatio-temporal input variables. Finally, we conclude that the SNN-QC offers a potential pathway for developing more accurate neuromorphic-quantum enhanced systems that are both energy-efficient and biologically-inspired, well-suited for dealing with spatio-temporal data.

EPJ Quantum Technology•Nov 11, 2025•3 citations
Advanced vision systems require retinomorphic, energy-efficient spike-based preprocessing of dynamic visual scenes. Here, we demonstrate multiple retinal preprocessing functionalities by leveraging a Hodgkin-Huxley-based optical spiking neuron (OSHN) that incorporates a two-dimensional anti-ambipolar phototransistor operated in the subthreshold regime to minimize power consumption. OSHN exhibits wavelength- and intensity-sensitive spike encoding with energy consumption per spike of 0.9 pJ under dark, 2 pJ at 480 nm (mid wavelength, M), and 24.5 pJ at 800 nm (long wavelength, L). The low (biological)-to-high spiking rate (0 - 2 kHz) with substantially faster response times (4.2 μμμs - 1.25 ms) than the human retina (30 ms - 60 ms), reveal OSHN's fast decision-making capability. OSHN facilitates concurrent spectral-spatial processing by emulating retinal antagonistic center-surround receptive fields (CSRFs) at a single wavelength (480 nm or 800 nm) with varying intensities, visual adaptation (at 480 nm) to prevent system saturation, and L-M cone opponency in midget ganglion cells. Finally, a CSRF-augmented spiking neural network (SNN) has been developed for camouflaged object detection, achieving 4.4%, 10.4%, and 28.4% improvements in accuracy over conventional SNN on FMNIST, COD10K, and synthetic camouflaged datasets, outperforming existing photoactive spiking architectures while enabling event-driven intelligent edge vision systems.
Traffic sign recognition is crucial for intelligent transportation and autonomous driving, as it can improve driving efficiency and ensure road safety. However, traditional recognition methods are based on large datasets and intensive computation, which limits their real-time applicability. Spiking Neural Networks (SNNs) offer a biologically inspired, energy-efficient alternative due to their spatiotemporal processing capabilities, but suffer from information loss and vanishing gradients during training. To overcome these limitations, this study proposes a Quantum Deep-supervised Spiking Neural Network (QDS-SNN) that integrates Quantum Neural Networks (QNNs) for efficient, low-power deep supervision. Using quantum superposition and entanglement, QNNs enable expressive representations and parallel computation, thereby enhancing performance without compromising energy efficiency. The proposed QDS-SNN incorporates a temporally and spatially adaptive LIF (TSA-LIF) neuron and a quantum-assisted classifier module (QACM) to mitigate gradient issues and improve training effectiveness. This study conducts experiments on the PennyLane quantum simulation platform, and the results show that QDS-SNN achieves 99.72\% accuracy on the GTSRB dataset in only 6 time steps -- outperforming the MS-ResNet baseline by 1.32\% while reducing energy consumption by 55.77\%. In the TSRD dataset, it achieves 97.90\% accuracy while reducing energy use to 52.68\% of the baseline. These results demonstrate that QDS-SNN offers a high-performance, energy-efficient solution for traffic sign recognition in intelligent transportation systems.
The rapid advancement of artificial intelligence (AI) and deep learning (DL) has catalyzed the emergence of several optimization-driven subfields, notably neuromorphic computing and quantum machine learning. Leveraging the differentiable nature of hybrid models, researchers have explored their potential to address complex problems through unified optimization strategies. One such development is the Spiking Quantum Neural Network (SQNN), which combines principles from spiking neural networks (SNNs) and quantum computing. However, existing SQNN implementations often depend on pretrained SNNs due to the non-differentiable nature of spiking activity and the limited scalability of current SNN encoders. In this work, we propose a novel architecture—Spiking-Quantum Data Re-upload Convolutional Neural Network (SQDR-CNN)—that enables joint training of convolutional SNNs and quantum circuits within a single backpropagation framework. Unlike its predecessor, SQDR-CNN allow convergence to reasonable performance without the reliance of pretrained spiking encoder and subsetting datasets. We also clarified some theoretical foundations, testing new design using quantum data-reupload with different training algorithm-initialization and evaluate the performance of the proposed model under noisy simulated quantum environments. As a result, we were able to achieve 86% of the mean top-performing accuracy of the state of the art (SOTA) SNN baselines, yet uses only 0.5% of the smallest spiking model’s parameters. Through this integration of neuromorphic and quantum paradigms, we aim to open new research directions and foster technological progress in multi-modal, learnable systems.
As the field of artificial intelligence experiences the emergence of various large-scale models, the computing power requirements are increasing. Simultaneously, Moore’s Law is approaching its limits, which intensifies the need to address how to perform high-dimensional complex data computations efficiently and with minimal energy consumption. Quantum computing and neuromorphic computing, with their unique features, offer potential solutions to this contemporary challenge. In this study, we aim to integrate quantum computing with neuromorphic computing, and develop a quantum spiking neural networks architecture. We proposed three measurement strategy to reducing operational costs, making it more friendly to near-term quantum hardware. We evaluated the performance of these three models on the standard MNIST dataset for classification tasks and found that they maintained a high level of accuracy despite a reduced number of parameters and a substantial decrease in the number of quantum circuit shots.
Abstract: Contemporary computational intelligence confronts a dual thermodynamic barrier: classical deep learning accelerators are throttled by the von Neumann memory-bus bottleneck and megawatt-scale power consumption, while gate-based quantum processors remain confined to multi-kilowatt cryogenic dilution refrigerators operating at millikelvin temperatures. In contrast, the biological human brain executes high-dimensional perceptual synthesis and continuous learning within a tight thermal envelope of approximately 20 W at physiological temperatures (T ≈ 310 K), leveraging event-driven sparse spiking dynamics and sub-cellular vibronic transport mechanisms. This monograph formalizes the theoretical foundations and solid-state circuit architecture for a Quantum Spiking Neural Network (QSNN) powered by room-temperature polarons and biomimetic phononics: (1) We model artificial quantum neurons using non-linear exciton-polarons in lithium niobate (LiNbO3) and diamond acoustic metamaterial waveguides, demonstrating threshold-driven coherent optical-acoustic pulse emission (< 100 ps) operating at ambient temperature (300 K); (2) We formulate a Non-Markovian Quantum Synaptic Plasticity Model, proving that structured vibronic phonon modes act as an intrinsic temporal memory kernel supporting quantum Spike-Timing-Dependent Plasticity (Q-STDP) with long-term retention (τ_ret > 10^3 s) without requiring cryogenic volatile refresh cycles; and (3) We derive the physical energy dissipation budget, proving that each quantum synaptic event consumes less than 1.8 fJ (femtojoules per spike)—three orders of magnitude below CMOS neuromorphic baselines. We establish non-equilibrium Bose-Hubbard Hamiltonians, synaptic update operators, and planar wafer-scale integration blueprints hosting 10^7 quantum neurons and 10^10 quantum synapses, establishing a non-von Neumann foundation for cryogen-free, brain-scale quantum cognitive computing.
The rapid advancement of artificial intelligence (AI) and deep learning (DL) has catalyzed the emergence of several optimization-driven subfields, notably neuromorphic computing and quantum machine learning. Leveraging the differentiable nature of hybrid models, researchers have explored their potential to address complex problems through unified optimization strategies. One such development is the Spiking Quantum Neural Network (SQNN), which combines principles from spiking neural networks (SNNs) and quantum computing. However, existing SQNN implementations often depend on pretrained SNNs due to the non-differentiable nature of spiking activity and the limited scalability of current SNN encoders. In this work, we propose a novel architecture, Spiking-Quantum Data Re-upload Convolutional Neural Network (SQDR-CNN), that enables joint training of convolutional SNNs and quantum circuits within a single backpropagation framework. Unlike its predecessor, SQDR-CNN allow convergence to reasonable performance without the reliance of pretrained spiking encoder and subsetting datasets. We also clarified some theoretical foundations, testing new design using quantum data-reupload with different training algorithm-initialization and evaluate the performance of the proposed model under noisy simulated quantum environments. As a result, we were able to achieve 86% of the mean top-performing accuracy of the SOTA SNN baselines, yet uses only 0.5% of the smallest spiking model's parameters. Through this integration of neuromorphic and quantum paradigms, we aim to open new research directions and foster technological progress in multi-modal, learnable systems.
Abstract The study introduces a hybrid computational framework that combines neuro-inspired information processing using spiking neural networks (SNN) and quantum information processing using quantum kernels to develop quantum-enhanced machine learning models, demonstrated through the classification of EEG data as a case study. In the proposed SNN-quantum kernel classifier (SNN-QC), SNN with spike time information representation is employed to learn spatio-temporal interactions (EEG recorded from multiple channels over time). Frequency-based (rate-based) information as spike frequency state vectors are extracted from the SNN and classified using a quantum classifier. In the latter part, we use the quantum kernel approach utilizing feature maps for classification tasks. The proposed SNN-QC is demonstrated on a benchmark EEG dataset to classify three distinct wrist movement tasks in six binary classification setups as a proof of concept. We introduce a novel feature map with high-order nonlinearity, which has outperformed current state-of-the-art feature maps and various machine learning methods in most of the case studies. Furthermore, the role of hyperparameters for enhanced feature maps is also highlighted. The performance of SNN-QC is evaluated using statistical metrics and cross-validation techniques, demonstrating its 1 efficacy across multiple binary classifiers. An experimental validation is also performed on an IBM QPU. The results demonstrate that the SNN-QC significantly outperforms the models that use statistical features rather than features extracted from the SNN as SNN accounts for the temporal interaction between the spatio-temporal input variables. Finally, we conclude that the SNN-QC offers a potential pathway for developing more accurate neuromorphic-quantum enhanced systems that are both energy-efficient and biologically-inspired, well-suited for dealing with spatio-temporal data.