Abstract
The neural network and quantum computing are both significant and appealing fields, with their interactive disciplines promising for large-scale computing tasks that are untackled by conventional computers. However, both developments are restricted by the scope of the hardware development. Nevertheless, many neural network algorithms had been proposed before GPUs became powerful enough for running very deep models. Similarly, quantum algorithms can also be proposed as knowledge reserve before real quantum computers are easily accessible. Specifically, taking advantage of both the neural networks and quantum computation and designing quantum deep neural networks (QDNNs) for acceleration on the Noisy Intermediate-Scale Quantum (NISQ) processors is also an important research problem. As one of the most widely used neural network architectures, convolutional neural network (CNN) remains to be accelerated by quantum mechanisms, with only a few attempts having been demonstrated. In this article, we propose a new hybrid quantum-classical circuit, namely, Quantum Fourier Convolutional Network (QFCN). Our model achieves exponential speedup compared with classical CNN theoretically and improves over the existing best result of quantum CNN. We demonstrate the potential of this architecture by applying it on different deep learning tasks, including traffic prediction and image classification.
- [1] . 2017. Quantum machine learning. Nature 549, 7671 (2017), 195–202.Google Scholar
Cross Ref
- [2] . 2020. YOLOv4: Optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934 (2020).Google Scholar
- [3] . 2018. Universal discriminative quantum neural networks. arXiv preprint arXiv:1805.08654 (2018).Google Scholar
- [4] . 2020. Acceleration of convolutional neural network using FFT-based split convolutions. arXiv preprint arXiv:2003.12621 (2020).Google Scholar
- [5] . 2019. Quantum convolutional neural networks. Nat. Phys. 15, 12 (2019), 1273–1278.Google Scholar
Cross Ref
- [6] . 2018. Adversarial attack on graph structured data. arXiv preprint arXiv:1806.02371 (2018).Google Scholar
- [7] . 2018. Quantum generative adversarial networks. Phys. Rev. A 98, 1 (2018), 012324.Google Scholar
Cross Ref
- [8] . 2018. BERT: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018).Google Scholar
- [9] . 2018. Machine learning & artificial intelligence in the quantum domain: A review of recent progress. Rep. Progr. Phys. 81, 7 (2018), 074001.Google Scholar
Cross Ref
- [10] . 2014. A quantum approximate optimization algorithm. arXiv preprint arXiv:1411.4028 (2014).Google Scholar
- [11] . 2020. Stacked spatio-temporal graph convolutional networks for action segmentation. In IEEE Winter Conference on Applications of Computer Vision. 576–585.Google Scholar
- [12] . 2019. From the quantum approximate optimization algorithm to a quantum alternating operator Ansatz. Algorithms 12, 2 (2019), 34.Google Scholar
Cross Ref
- [13] . 2000. An improved quantum Fourier transform algorithm and applications. In 41st Annual Symposium on Foundations of Computer Science. IEEE, 515–525.Google Scholar
- [14] . 2016. Deep residual learning for image recognition. In IEEE Conference on Computer Vision and Pattern Recognition. 770–778.Google Scholar
Cross Ref
- [15] . 2020. Recurrent neural network wave functions. Phys. Rev. Res. 2, 2 (2020), 023358.Google Scholar
Cross Ref
- [16] . 2017. Densely connected convolutional networks. In IEEE Conference on Computer Vision and Pattern Recognition. 4700–4708.Google Scholar
Cross Ref
- [17] . 2020. Quantum Fourier analysis. Proc. Nat. Acad. Sci. 117, 20 (2020), 10715–10720.Google Scholar
Cross Ref
- [18] . 2019. A style-based generator architecture for generative adversarial networks. In IEEE Conference on Computer Vision and Pattern Recognition. 4401–4410.Google Scholar
Cross Ref
- [19] . 2019. q-means: A quantum algorithm for unsupervised machine learning. In International Conference on Advances in Neural Information Processing Systems. 4134–4144.Google Scholar
- [20] . 2019. Quantum algorithms for deep convolutional neural networks. In International Conference on Learning Representations.Google Scholar
- [21] . 2016. Quantum recommendation systems. arXiv preprint arXiv:1603.08675 (2016).Google Scholar
- [22] . 2020. Quantum gradient descent for linear systems and least squares. Phys. Rev. A 101, 2 (2020), 022316.Google Scholar
Cross Ref
- [23] . 2017. Semi-supervised classification with graph convolutional networks. In International Conference on Learning Representations.Google Scholar
- [24] . 2020. FALCON: A Fourier transform based approach for fast and secure convolutional neural network predictions. In IEEE/CVF Conference on Computer Vision and Pattern Recognition. 8705–8714.Google Scholar
Cross Ref
- [25] . 2017. Diffusion convolutional recurrent neural network: Data-driven traffic forecasting. arXiv preprint arXiv:1707.01926 (2017).Google Scholar
- [26] . 2013. Quantum algorithms for supervised and unsupervised machine learning. arXiv preprint arXiv:1307.0411 (2013).Google Scholar
- [27] . 2014. Quantum principal component analysis. Nat. Phys. 10, 9 (2014), 631–633.Google Scholar
Cross Ref
- [28] . 2018. Quantum generative adversarial learning. Phys. Rev. Lett. 121, 4 (2018), 040502.Google Scholar
Cross Ref
- [29] . 2003. Quantum convolution and quantum correlation algorithms are physically impossible. arXiv preprint quant-ph/0309070 (2003).Google Scholar
- [30] . 2019. Windowed Fourier transform and general wavelet algorithms in quantum computation. Quant. Inf. Computat. 19, 3–4 (2019), 237–251.Google Scholar
Digital Library
- [31] . 2018. Barren plateaus in quantum neural network training landscapes. Nat. Commun. 9, 1 (2018), 1–6.Google Scholar
Cross Ref
- [32] . 2016. The theory of variational hybrid quantum-classical algorithms. New J. Phys. 18, 2 (2016), 023023.Google Scholar
Cross Ref
- [33] . 2019. Predicting quantum advantage by quantum walk with convolutional neural networks. New J. Phys. 21, 12 (2019), 125002.Google Scholar
Cross Ref
- [34] . 2006. Generic quantum Fourier transforms. ACM Trans. Algor. 2, 4 (2006), 707–723.Google Scholar
Digital Library
- [35] . 2020. Circuit implementation of bucket brigade qRAM for quantum state preparation. arXiv e-prints (2020), arXiv–2006.Google Scholar
- [36] . 2018. Image to image translation for domain adaptation. In IEEE Conference on Computer Vision and Pattern Recognition. 4500–4509.Google Scholar
Cross Ref
- [37] . 2002. Quantum Computation and Quantum Information. Cambridge University Press.Google Scholar
- [38] . 1981. The fast Fourier transform. In Fast Fourier Transform and Convolution Algorithms. Springer, 80–111.Google Scholar
Cross Ref
- [39] . 2019. Circuit-based quantum random access memory for classical data. Sci. Rep. 9, 1 (2019), 1–8.Google Scholar
- [40] . 2014. A variational eigenvalue solver on a photonic quantum processor. Nat. Comm. 5 (2014), 4213.Google Scholar
Cross Ref
- [41] . 2017. FCNN: Fourier convolutional neural networks. In Joint European Conference on Machine Learning and Knowledge Discovery in Databases. Springer, 786–798.Google Scholar
Cross Ref
- [42] . 2018. Quantum computing in the NISQ era and beyond. Quantum 2 (2018), 79.Google Scholar
- [43] . 2014. Quantum support vector machine for big data classification. Phys. Rev. Lett. 113, 13 (2014), 130503.Google Scholar
Cross Ref
- [44] . 2016. You only look once: Unified, real-time object detection. In IEEE Conference on Computer Vision and Pattern Recognition. 779–788.Google Scholar
Cross Ref
- [45] . 2001. Molecular random access memory cell. Appl. Phys. Lett. 78, 23 (2001), 3735–3737.Google Scholar
Cross Ref
- [46] . 2015. Spectral representations for convolutional neural networks. In International Conference on Advances in Neural Information Processing Systems. 2449–2457.Google Scholar
- [47] . 1986. Learning representations by back-propagating errors. Nature 323, 6088 (1986), 533–536.Google Scholar
Cross Ref
- [48] . 2020. Layerwise learning for quantum neural networks. arXiv preprint arXiv:2006.14904 (2020).Google Scholar
- [49] . 2018. A case for variability-aware policies for NISQ-era quantum computers. arXiv preprint arXiv:1805.10224 (2018).Google Scholar
- [50] . 2019. Quantum graph neural networks. arXiv preprint arXiv:1909.12264 (2019).Google Scholar
- [51] . 2014. Quantum algorithms for nearest-neighbor methods for supervised and unsupervised learning. arXiv preprint arXiv:1401.2142 (2014).Google Scholar
- [52] . 1978. On computing the discrete Fourier transform. Math. Computat. 32, 141 (1978), 175–199.Google Scholar
Cross Ref
- [53] . 2020. A comprehensive survey on graph neural networks. IEEE Trans. Neural Netw. Learn. Syst. 32, 1 (2020).Google Scholar
- [54] . 2021. Decentralizing feature extraction with quantum convolutional neural network for automatic speech recognition. In IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP’21). IEEE, 6523–6527.Google Scholar
Cross Ref
- [55] . 2017. Spatio-temporal graph convolutional networks: A deep learning framework for traffic forecasting. arXiv preprint arXiv:1709.04875 (2017).Google Scholar
- [56] . 2019. QDNN: DNN with quantum neural network layers. arXiv preprint arXiv:1912.12660 (2019).Google Scholar
- [57] . 2020. Where to go next: A spatio-temporal gated network for next PoI recommendation. IEEE Trans. Knowl. Data Eng. 34, 5 (2020).Google Scholar
Cross Ref
Index Terms
Quantum Fourier Convolutional Network
Recommendations
A Leap among Quantum Computing and Quantum Neural Networks: A Survey
In recent years, Quantum Computing witnessed massive improvements in terms of available resources and algorithms development. The ability to harness quantum phenomena to solve computational problems is a long-standing dream that has drawn the scientific ...
Quantum Entanglement-based Deep Convolutional Neural Networks
CompSysTech '20: Proceedings of the 21st International Conference on Computer Systems and TechnologiesThe paper presents a quantum-based approach for modeling deep neural networks. Quantum entanglement-based neural network model is described, that utilizes several quantum phenomena applied to the connections of the network structures. The concept of ...
RGB image classification with quantum convolutional ansatz
AbstractWith the rapid growth of qubit numbers and coherence times in quantum hardware technology, implementing shallow neural networks on the so-called Noisy Intermediate-Scale Quantum (NISQ) devices has attracted a lot of interest. Many quantum (...






Comments