ABSTRACT
Quantum computers promise significant advantages over classical computers for a number of different applications. We show that the complete loss function landscape of a neural network can be represented as the quantum state output by a quantum computer. We demonstrate this explicitly for a binary neural network and, further, show how a quantum computer can train the network by manipulating this state using a well-known algorithm known as quantum amplitude amplification. We further show that with minor adaptation, this method can also represent the meta-loss landscape of a number of neural network architectures simultaneously. We search this meta-loss landscape with the same method to simultaneously train and design a binary neural network.
- Gilles Brassard, Peter Hoyer, Michele Mosca, and Alain Tapp. 2002. Quantum amplitude amplification and estimation. Contemp. Math. 305 (2002), 53--74.Google ScholarCross Ref
- Yudong Cao, Gian Giacomo Guerreschi, and Alán Aspuru-Guzik. 2017. Quantum Neuron: an elementary building block for machine learning on quantum computers. arXiv preprint arXiv:1711.11240 (2017).Google Scholar
- Anna Choromanska, Yann LeCun, and Gérard Ben Arous. 2015. Open problem: The landscape of the loss surfaces of multilayer networks. In Conference on Learning Theory. 1756--1760.Google Scholar
- Carlo Ciliberto, Mark Herbster, Alessandro Davide Ialongo, Massimiliano Pontil, Andrea Rocchetto, Simone Severini, and Leonard Wossnig. 2018. Quantum machine learning: a classical perspective. Proc. R. Soc. A 474, 2209 (2018), 20170551.Google ScholarCross Ref
- Matthieu Courbariaux, Itay Hubara, Daniel Soudry, Ran El-Yaniv, and Yoshua Bengio. 2016. Binarized neural networks: Training deep neural networks with weights and activations constrained to+ 1 or-1. arXiv preprint arXiv:1602.02830 (2016).Google Scholar
- Adenilton José da Silva, Teresa Bernarda Ludermir, and Wilson Rosa de Oliveira. 2016. Quantum perceptron over a field and neural network architecture selection in a quantum computer. Neural Networks 76 (2016), 55--64. Google ScholarDigital Library
- Pierre-Luc Dallaire-Demers and Nathan Killoran. 2018. Quantum generative adversarial networks. arXiv preprint arXiv:1804.08641 (2018).Google Scholar
- Vittorio Giovannetti, Seth Lloyd, and Lorenzo Maccone. 2008. Quantum random access memory. Physical review letters 100, 16 (2008), 160501.Google Scholar
- Lov K Grover. 1996. A fast quantum mechanical algorithm for database search. In Proceedings of the twenty-eighth annual ACM symposium on Theory of computing. ACM, 212--219. Google ScholarDigital Library
- Aram W Harrow, Avinatan Hassidim, and Seth Lloyd. 2009. Quantum algorithm for linear systems of equations. Physical review letters 103, 15 (2009), 150502.Google Scholar
- Ashish Kapoor, Nathan Wiebe, and Krysta Svore. 2016. Quantum perceptron models. In Advances in Neural Information Processing Systems. 3999--4007.Google Scholar
- Sam Leroux, Steven Bohez, Tim Verbelen, Bert Vankeirsbilck, Pieter Simoens, and Bart Dhoedt. 2017. Transfer Learning with Binary Neural Networks. arXiv preprint arXiv:1711.10761 (2017).Google Scholar
- Xiaofan Lin, Cong Zhao, and Wei Pan. 2017. Towards accurate binary convolutional neural network. In Advances in Neural Information Processing Systems. 345--353. Google ScholarDigital Library
- Seth Lloyd, Masoud Mohseni, and Patrick Rebentrost. 2013. Quantum algorithms for supervised and unsupervised machine learning. arXiv preprint arXiv:1307.0411 (2013).Google Scholar
- Harmut Neven, Vasil S Denchev, Marshall Drew-Brook, Jiayong Zhang, William G Macready, and Geordie Rose. 2009. NIPS 2009 demonstration: Binary classification using hardware implementation of quantum annealing. (2009).Google Scholar
- Mohammad Rastegari, Vicente Ordonez, Joseph Redmon, and Ali Farhadi. 2016. Xnor-net: Imagenet classification using binary convolutional neural networks. In European Conference on Computer Vision. Springer, 525--542.Google ScholarCross Ref
- Bob Ricks and Dan Ventura. 2004. Training a quantum neural network. In Advances in neural information processing systems. 1019--1026. Google ScholarDigital Library
- Damian S Steiger, Thomas Häner, and Matthias Troyer. 2018. ProjectQ: an open source software framework for quantum computing. Quantum 2 (2018), 49.Google ScholarCross Ref
- Edwin Stoudenmire and David J Schwab. 2016. Supervised Learning with Tensor Networks. In Advances in Neural Information Processing Systems 29. 4799--4807. Google ScholarDigital Library
- Edwin Stoudenmire and David J Schwab. 2016. Supervised learning with tensor networks. In Advances in Neural Information Processing Systems. 4799--4807. Google ScholarDigital Library
- Ewin Tang. 2018. A quantum-inspired classical algorithm for recommendation systems. arXiv preprint arXiv:1807.04271 (2018).Google Scholar
- Wei Tang, Gang Hua, and Liang Wang. 2017. How to train a compact binary neural network with high accuracy?. In AAAI. 2625--2631. Google ScholarDigital Library
- Chris Thornton. 1996. Parity: the problem that won't go away. In Conference of the Canadian Society for Computational Studies of Intelligence. Springer, 362--374. Google ScholarDigital Library
- Christof Zalka. 1999. Grover's quantum searching algorithm is optimal. Physical Review A 60, 4 (1999), 2746.Google ScholarCross Ref
- Training and Meta-Training Binary Neural Networks with Quantum Computing
Recommendations
Quantum Algorithms for Feedforward Neural Networks
Quantum machine learning has the potential for broad industrial applications, and the development of quantum algorithms for improving the performance of neural networks is of particular interest given the central role they play in machine learning ...
Training and meta-training an ensemble of binary neural networks with quantum computing
AbstractThe design of NNs requires an expensive search in the space of the neural network architecture. This search performs heuristics called Neural Architecture Search (NAS), but an efficient algorithmic NAS remains an open problem. The development of ...
Visualization of the Quantum Fourier Transform Using a Quantum Computer Simulator
The quantum Fourier transform (QFT) is a key subroutine of quantum algorithms for factoring and simulation and is the heart of the hidden-subgroup problem, the solution of which is expected to lead to the development of new quantum algorithms. The QFT ...
Comments