Parameter efficient hybrid spiking-quantum convolutional neural network with surrogate gradient and quantum data-reupload
Authors:
Preprint
Abstract
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.Keywords
All Related Versions
This publication has 33 references indexed in Scilit:
- Parallel proportional fusion of a spiking quantum neural network for optimizing image classificationApplied Intelligence, 2024
- Data re-uploading with a single quditQuantum Machine Intelligence, 2023
- A shallow hybrid classical–quantum spiking feedforward neural network for noise-robust image classificationApplied Soft Computing, 2023
- Accelerating spiking neural networks using quantum algorithm with high success probability and high calculation accuracyNeurocomputing, 2022
- Hybrid quantum-classical convolutional neural networksScience China Physics, Mechanics & Astronomy, 2021
- Quantum superposition inspired spiking neural networkiScience, 2021
- Quanvolutional neural networks: powering image recognition with quantum circuitsQuantum Machine Intelligence, 2020
- Deep neural networks with weighted spikesNeurocomputing, 2018
- Hardware-efficient variational quantum eigensolver for small molecules and quantum magnetsNature, 2017
- Approximation capabilities of multilayer feedforward networksNeural Networks, 1991