On hybrid quanvolutional neural networks optimization
Open Access
- 10 February 2025
- journal article
- research article
- Published by Springer Nature in Quantum Machine Intelligence
- Vol. 7 (1) , 1-17
Abstract
This paper investigates the optimization properties of hybrid quantum-classical quanvolutional neural networks (QuanvNNs), i.e., hybrid architectures merging quanvolutional layers with classical dense layers. We explore several optimization strategies by assessing 9 optimizers across various configurations of layers and kernel size. Through rigorous experimentation, it was found that optimizers such as Adabelief, RMSProp, and Adam outperform others, showcasing high accuracy scores. Conversely, Fromage, SM3, and Adagrad exhibit notably lower performance, highlighting the difficulty of effectively navigating the loss landscape. These findings emphasize the critical role of optimizer selection in a gradient-based variational optimization strategy. Additionally, quanvolutional layer parameters exhibit minimal fluctuations during the training phase, while classical parameters undergo variations on an order of magnitude higher. This disparity suggests a distinct behavior in the optimization dynamics between quantum and classical components, potentially influencing the efficacy of each layer type and offering valuable insights into the underlying mechanisms governing quanvolutional filters. We also evaluate QuanvNN robustness through comparisons against classical CNNs in scenarios involving few-shot learning and input perturbations. Our experimental findings underscore not only enhanced convergence capabilities of QuanvNNs, but also emphasize their superior efficacy in handling severely perturbed inputs. Finally, a randomized QuanvNN variant is tested, yielding comparable performance to optimized models as suggested by previous experiments on parameters variation. All these findings underscore the potential of QuanvNNs in offering robustness and optimization potential compared to their classical counterparts, with implications for quantum-enhanced machine learning.Keywords
Funding Information
- Università degli Studi di Roma La Sapienza
This publication has 26 references indexed in Scilit:
- A Lie algebraic theory of barren plateaus for deep parameterized quantum circuitsNature Communications, 2024
- Resource saving via ensemble techniques for quantum neural networksQuantum Machine Intelligence, 2023
- Stereoscopic scalable quantum convolutional neural networksNeural Networks, 2023
- Quanvolutional Neural Network Applied to MNIST2023
- Noise-induced barren plateaus in variational quantum algorithmsNature Communications, 2021
- The power of quantum neural networksNature Computational Science, 2021
- Power of data in quantum machine learningNature Communications, 2021
- Quanvolutional neural networks: powering image recognition with quantum circuitsQuantum Machine Intelligence, 2020
- Barren plateaus in quantum neural network training landscapesNature Communications, 2018
- Quantum machine learningNature, 2017