Recently, quantum machine learning has been ap-plied to stochastic-based modelling, promising that the inherent uncertainty in quantum computing will be a significant advan-tage, driving neuromorphic computing research to new heights. Spiking Neural Networks (SNNs) and their neuromorphic are gaining popularity due to their inherent ability to process spatial and temporal data. However, learning the interconnection weights is daunting due to the inherent stochastic characteristics of neuron signals and the inherent non-differentiable spike events in classical SNN. This paper introduces a supervised Deep Spiking Quantum Neural Network (DSQ-Net) using a hybrid quantum- classical architecture having the merits of amplitude encoding in a dressed quantum layer. A novel attempt has been made to obviate the challenges in training a classical deep SNN, assisted by a Variational Quantum Circuit (VQC) in the proposed hy-brid quantum-classical framework. The DSQ-Net has undergone thorough validation and benchmarking procedures using the PennyLane Quantum Simulator and the limited volume real IBM Quantum hardware. The experiments have been conducted on images from the MNIST, FashionMNIST, KMNIST, and CIFAR-I0 datasets. Classification accuracy has been reported in the high nineties for unseen noisy test images using the proposed DSQ-Net model on the quantum simulator. It outper-forms its classical counterpart (Deep Spiking Neural Networks), shallow Random Quantum Neural Networks (RQNN), Quantum Superposition-inspired Spiking Neural Networks (SQIN), ResNet- 18, and AlexNet. The PyTorch implementation of DSQ-Net is made available on Github11https://anonymous.4open.science/r/DSQ-Net-037E,
Recently, quantum machine learning has been ap-plied to stochastic-based modelling, promising that the inherent uncertainty in quantum computing will be a significant advan-tage, driving neuromorphic computing research to new heights. Spiking Neural Networks (SNNs) and their neuromorphic are gaining popularity due to their inherent ability to process spatial and temporal data. However, learning the interconnection weights is daunting due to the inherent stochastic characteristics of neuron signals and the inherent non-differentiable spike events in classical SNN. This paper introduces a supervised Deep Spiking Quantum Neural Network (DSQ-Net) using a hybrid quantum- classical architecture having the merits of amplitude encoding in a dressed quantum layer. A novel attempt has been made to obviate the challenges in training a classical deep SNN, assisted by a Variational Quantum Circuit (VQC) in the proposed hy-brid quantum-classical framework. The DSQ-Net has undergone thorough validation and benchmarking procedures using the PennyLane Quantum Simulator and the limited volume real IBM Quantum hardware. The experiments have been conducted on images from the MNIST, FashionMNIST, KMNIST, and CIFAR-I0 datasets. Classification accuracy has been reported in the high nineties for unseen noisy test images using the proposed DSQ-Net model on the quantum simulator. It outper-forms its classical counterpart (Deep Spiking Neural Networks), shallow Random Quantum Neural Networks (RQNN), Quantum Superposition-inspired Spiking Neural Networks (SQIN), ResNet- 18, and AlexNet. The PyTorch implementation of DSQ-Net is made available on Github11https://anonymous.4open.science/r/DSQ-Net-037E,
Classical Random Neural Networks (RNNs) have demonstrated effective applications in decision making, signal processing, and image recognition tasks. However, their implementation has been limited to deterministic digital systems that output probability distributions in lieu of stochastic behaviors of random spiking signals. We introduce the novel class of supervised Random Quantum Neural Networks (RQNNs) with a robust training strategy to better exploit the random nature of the spiking RNN. The proposed RQNN employs hybrid classical-quantum algorithms with superposition state and amplitude encoding features, inspired by quantum information theory and the brain's spatial-temporal stochastic spiking property of neuron information encoding. We have extensively validated our proposed RQNN model, relying on hybrid classical-quantum algorithms via the PennyLane Quantum simulator with a limited number of \emph{qubits}. Experiments on the MNIST, FashionMNIST, and KMNIST datasets demonstrate that the proposed RQNN model achieves an average classification accuracy of 94.9%. Additionally, the experimental findings illustrate the proposed RQNN's effectiveness and resilience in noisy settings, with enhanced image classification accuracy when compared to the classical counterparts (RNNs), classical Spiking Neural Networks (SNNs), and the classical convolutional neural network (AlexNet). Furthermore, the RQNN can deal with noise, which is useful for various applications, including computer vision in NISQ devices. The PyTorch code (https://github.com/darthsimpus/RQN) is made available on GitHub to reproduce the results reported in this manuscript.
The application of classical Random Neural Networks (RNN) has been restricted to deterministic digital systems that generate probability distributions instead of the stochastic characteristics of random spiking signals. To optimize the utilization of the stochastic properties inherent in RNN, we propose a new category of supervised Random Quantum Neural Networks (RQNN) that incorporate a resilient training methodology. The RQNN under consideration utilizes a combination of classical and quantum algorithms, incorporating superposition state and angle encoding characteristics that draw inspiration from quantum information theory. Additionally, the model incorporates the stochastic random spiking property of neuron information encoding, which is known to exhibit spatial-temporal features similar to those observed in the brain. The proposed RQNN model has undergone thorough validation, relying on hybrid classical-quantum algorithms through a real IBM quantum processor. The proposed RQNN model is tested on the MNIST, Fashion-MNIST, and KMNIST datasets. The results indicate that it achieved an average classification accuracy of 59.6% when presented with unseen noisy test images. The experimental results demonstrate the efficacy and robustness of the proposed RQNN11The early version of the work is posted in arXiv: https://doi.org/10.48550/arXiv.2203.01764. in classifying noisy images that have not been previously encountered.
Abstract The extreme parallelism property warrant convergence of neural networks with that of quantum computing. As the size of the network grows, the classical implementation of neural networks becomes computationally expensive and not feasible. In this paper, we propose a hybrid image classifier model using spiking neural networks (SNN) and quantum circuits that combines dynamic behaviour of SNN with the extreme parallelism offered by quantum computing. The proposed model outperforms models in comparison with spiking neural network in classical computing, and hybrid convolution neural network-quantum circuit models in terms of various performance parameters. The proposed hybrid SNN-QC model achieves an accuracy of 99.9% in comparison with CNN-QC model accuracy of 96.3%, and SNN model of accuracy 91.2% in MNIST classification task. The tests on KMNIST and CIFAR-1O also showed improvements.
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.
Neuromorphic and quantum computing have recently emerged as promising paradigms for advancing artificial intelligence, each offering complementary strengths. Neuromorphic systems built on spiking neurons excel at processing time series data efficiently through sparse, event-driven computation, consuming energy only upon input events. Quantum computing, on the other hand, operates on state spaces that grow exponentially in dimension with the number of qubits -- as a consequence of tensor-product composition -- with quantum states admitting superposition across basis states and entanglement between subsystems. Hybrid approaches combining these paradigms have begun to show potential, but existing quantum spiking models have important limitations. Notably, they implement classical memory mechanisms on single qubits, requiring repeated measurements to estimate firing probabilities, while relying on conventional backpropagation for training. In this paper, we propose a novel stochastic quantum spiking (SQS) neuron model that addresses these challenges. The SQS neuron uses multi-qubit quantum circuits to realize a spiking unit with internal quantum memory, enabling event-driven probabilistic spike generation in a single shot during inference. Furthermore, we study networks of SQS neurons, dubbed SQS neural networks (SQSNN), and demonstrate that they can be trained via a hardware-friendly local learning rule, eliminating the need for global classical backpropagation. The proposed SQSNN model is shown via experiments with both conventional and neuromorphic datasets to improve over previous quantum spiking neural networks, as well as over classical counterparts, when fixing the overall number of trainable parameters, highlighting its potential for event-driven applications such as neuromorphic integrated sensing and communications (N-ISAC).
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.