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

TL;DR

This paper introduces a hybrid spiking-quantum convolutional neural network that enables joint training without pretrained encoders, achieving high accuracy with significantly fewer parameters in noisy quantum environments.

Contribution

The novel SQDR-CNN architecture allows end-to-end training of spiking neural networks and quantum circuits, overcoming previous limitations of non-differentiability and scalability.

Findings

Achieved 86% of state-of-the-art SNN accuracy.

Uses only 0.5% of the parameters of the smallest spiking models.

Performs well under noisy quantum simulation environments.

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.