Abstract
Quantum convolutional neural networks encapsulate and combine complex features of both Artificial intelligence and principles of Quantum Mechanics to develop complex systems capable of solving intricate and detailed machine learning problems such as object recognition.
In this paper, we propose an experimental design for a quantum convolutional neural network to be used in conjunction with the GTSRB dataset and compare the results to that of both a traditional neural network and a hybrid neural network, enabling an accurate comparison between the various methods. A detailed look into the mathematical and architectural constructs of the QCNN will be depicted alongside the potential flaws that Quantum computing may incur.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Ayten, B.: Activation functions in deep neural network (2021). https://medium.datadriveninvestor.com/activation-functions-in-deep-neural-network-4d8849b70046
Brownlee, J.: Definition of an epoch (2022). https://machinelearningmastery.com/difference-between-a-batch-and-an-epoch/#:~:text=The%20number%20of%20epochs%20is%20a%20hyperparameter%20that%20defines%20the,update%20the%20internal%20model%20parameters
Cong, I.: Original quantum neural network (2018). https://arxiv.org/abs/1810.03787
Cong, I.: Quantum convolutional neural networks (2019). https://www.researchgate.net/publication/335412116_Quantum_convolutional_neural_networks/download
Hari Dass, N.D.: Quantum superposition (2013). https://www.sciencedirect.com/topics/engineering/gaussian-filter, https://www.researchgate.net/publication/258566887_The_Superposition_Principle_in_Quantum_Mechanics_-_did_the_rock_enter_the_foundation_surreptitiously
Kjaergaard, M.: et al. Density matrix exponentiation (2022). https://journals.aps.org/prx/abstract/10.1103/PhysRevX.12.011005
Hong, C.: Photonic scheme of quantum phase estimation for quantum algorithms via cross-Kerr nonlinearities under decoherence effect (2019). https://opg.optica.org/DirectPDFAccess/375E153B-D1CC-4693-8A25D3377EE09486_422230/oe-27-21-31023.pdf?da=1 &id=422230 &seq=0 &mobile=no
Liu, W.: Quantum searchable encryption for cloud data based on full-blind quantum computation (2019). https://www.semanticscholar.org/paper/Quantum-Searchable-Encryption-for-Cloud-Data-Based-Liu-Xu/7d53d3b8604e9f2eace450c931e971a44ba52017
Institut Fur Neuroinformatik. Gtsrb results (2011). https://benchmark.ini.rub.de/gtsrb_results.html
University of Queensland. Mera architecture (2008). http://msl.cs.uiuc.edu/~lavalle/papers/LavKuf01.pdf
Parveez, S.: Underfitting & overfitting - the thwarts of machine learning models’ accuracy (2020). https://towardsai.net/p/machine-learning/underfitting-overfitting
Pennylane. Quantum neural network definition (2021). https://pennylane.ai/qml/glossary/quantum_neural_network.html
Isaac Physics. Superposition principle (2021). https://isaacphysics.org/concepts/cp_superposition?stage=all
QuantumMAgazine. Job one for quantum computers: boost artificial intelligence (2019). https://www.quantamagazine.org/job-one-for-quantum-computers-boost-artificial-intelligence-20180129/
Rebinowitz, M.: Wave particle duality (2003). https://arxiv.org/pdf/physics/0302062.pdf
Remanan, K.S.: Beginner’s guide to quantum machine learning (2021). https://blog.paperspace.com/beginners-guide-to-quantum-machine-learning/
Tucci, R.R.: Unitary matrices (2005). https://arxiv.org/abs/quant-ph/0507171
Singh, R.: Principal component analysis (PCA) with code on MNIST dataset (2019). https://medium.com/analytics-vidhya/principal-component-analysis-pca-with-code-on-mnist-dataset-da7de0d07c22
Stallkamp, J.: Man vs. computer: benchmarking machine learning algorithms for traffic sign recognition. Neural Netw. 32, 323–332 (2012). https://doi.org/10.1016/j.neunet.2012.02.016
Tensorflow. Qcnn result (2021). https://www.tensorflow.org/quantum/tutorials/qcnn
Cornell University. Yolo model (2021). https://arxiv.org/abs/1506.02640
Yu, H., Zhang, J.J.: Principle component analysis (2020). https://www.intechopen.com/chapters/10210
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Cox, D. (2023). Experimental Design of a Quantum Convolutional Neural Network Solution for Traffic Sign Recognition. In: Arai, K. (eds) Intelligent Systems and Applications. IntelliSys 2022. Lecture Notes in Networks and Systems, vol 542. Springer, Cham. https://doi.org/10.1007/978-3-031-16072-1_44
Download citation
DOI: https://doi.org/10.1007/978-3-031-16072-1_44
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-16071-4
Online ISBN: 978-3-031-16072-1
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)