{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,20]],"date-time":"2026-01-20T04:52:38Z","timestamp":1768884758464,"version":"3.49.0"},"reference-count":55,"publisher":"MDPI AG","issue":"5","license":[{"start":{"date-parts":[[2018,5,18]],"date-time":"2018-05-18T00:00:00Z","timestamp":1526601600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Entropy"],"abstract":"<jats:p>Training deep learning networks is a difficult task due to computational complexity, and this is traditionally handled by simplifying network topology to enable parallel computation on graphical processing units (GPUs). However, the emergence of quantum devices allows reconsideration of complex topologies. We illustrate a particular network topology that can be trained to classify MNIST data (an image dataset of handwritten digits) and neutrino detection data using a restricted form of adiabatic quantum computation known as quantum annealing performed by a D-Wave processor. We provide a brief description of the hardware and how it solves Ising models, how we translate our data into the corresponding Ising models, and how we use available expanded topology options to explore potential performance improvements. Although we focus on the application of quantum annealing in this article, the work discussed here is just one of three approaches we explored as part of a larger project that considers alternative means for training deep learning networks. The other approaches involve using a high performance computing (HPC) environment to automatically find network topologies with good performance and using neuromorphic computing to find a low-power solution for training deep learning networks. Our results show that our quantum approach can find good network parameters in a reasonable time despite increased network topology complexity; that HPC can find good parameters for traditional, simplified network topologies; and that neuromorphic computers can use low power memristive hardware to represent complex topologies and parameters derived from other architecture choices.<\/jats:p>","DOI":"10.3390\/e20050380","type":"journal-article","created":{"date-parts":[[2018,5,21]],"date-time":"2018-05-21T04:07:30Z","timestamp":1526875650000},"page":"380","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":27,"title":["Adiabatic Quantum Computation Applied to Deep Learning Networks"],"prefix":"10.3390","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7229-9417","authenticated-orcid":false,"given":"Jeremy","family":"Liu","sequence":"first","affiliation":[{"name":"Department of Computer Science, University of Southern California, Los Angeles, CA 90089, USA"},{"name":"Information Sciences Institute, University of Southern California, Marina del Rey, CA 90292, USA"}]},{"given":"Federico M.","family":"Spedalieri","sequence":"additional","affiliation":[{"name":"Information Sciences Institute, University of Southern California, Marina del Rey, CA 90292, USA"},{"name":"Department of Electrical Engineering, University of Southern California, Los Angeles, CA 90089, USA"}]},{"given":"Ke-Thia","family":"Yao","sequence":"additional","affiliation":[{"name":"Information Sciences Institute, University of Southern California, Marina del Rey, CA 90292, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6687-3435","authenticated-orcid":false,"given":"Thomas E.","family":"Potok","sequence":"additional","affiliation":[{"name":"Computational Data Analytics Group, Oak Ridge National Laboratory, Oak Ridge, TN 37830, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4264-8097","authenticated-orcid":false,"given":"Catherine","family":"Schuman","sequence":"additional","affiliation":[{"name":"Computational Data Analytics Group, Oak Ridge National Laboratory, Oak Ridge, TN 37830, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0591-4330","authenticated-orcid":false,"given":"Steven","family":"Young","sequence":"additional","affiliation":[{"name":"Computational Data Analytics Group, Oak Ridge National Laboratory, Oak Ridge, TN 37830, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8101-0571","authenticated-orcid":false,"given":"Robert","family":"Patton","sequence":"additional","affiliation":[{"name":"Computational Data Analytics Group, Oak Ridge National Laboratory, Oak Ridge, TN 37830, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3070-4087","authenticated-orcid":false,"given":"Garrett S.","family":"Rose","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering &amp; Computer Science, University of Tennessee, Knoxville, TN 37996, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7936-2175","authenticated-orcid":false,"given":"Gangotree","family":"Chamka","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering &amp; Computer Science, University of Tennessee, Knoxville, TN 37996, USA"}]}],"member":"1968","published-online":{"date-parts":[[2018,5,18]]},"reference":[{"key":"ref_1","first-page":"147","article-title":"A learning algorithm for Boltzmann machines","volume":"9","author":"Ackley","year":"1985","journal-title":"Cogn. Sci."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"504","DOI":"10.1126\/science.1127647","article-title":"Reducing the Dimensionality of Data with Neural Networks","volume":"313","author":"Hinton","year":"2006","journal-title":"Science"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1527","DOI":"10.1162\/neco.2006.18.7.1527","article-title":"A Fast Learning Algorithm for Deep Belief Nets","volume":"18","author":"Hinton","year":"2006","journal-title":"Neural Comput."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"2278","DOI":"10.1109\/5.726791","article-title":"Gradient-based learning applied to document recognition","volume":"86","author":"LeCun","year":"1998","journal-title":"Proc. IEEE"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Scherer, D., M\u00fcller, A., and Behnke, S. (2010). Evaluation of pooling operations in convolutional architectures for object recognition. International Conference on Artificial Neural Networks, Springer.","DOI":"10.1007\/978-3-642-15825-4_10"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"11441","DOI":"10.1073\/pnas.1604850113","article-title":"Convolutional networks for fast, energy-efficient neuromorphic computing","volume":"113","author":"Esser","year":"2016","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Indiveri, G., Corradi, F., and Qiao, N. (2015, January 7\u20139). Neuromorphic Architectures for Spiking Deep Neural Networks. Proceedings of the IEEE International Electron Devices Meeting (IEDM), Washington, DC, USA.","DOI":"10.1109\/IEDM.2015.7409623"},{"key":"ref_8","first-page":"0541","article-title":"Quantum deep learning","volume":"16","author":"Wiebe","year":"2016","journal-title":"Quantum Inf. Comput."},{"key":"ref_9","unstructured":"LeCun, Y., Cortes, C., and Burges, C.J. (2018, May 17). The MNIST Database of Handwritten Digits. Available online: http:\/\/yann.lecun.com\/exdb\/mnist\/."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"467","DOI":"10.1007\/BF02650179","article-title":"Simulating physics with computers","volume":"21","author":"Feynman","year":"1982","journal-title":"Int. J. Theor. Phys."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"1484","DOI":"10.1137\/S0097539795293172","article-title":"Polynomial-Time Algorithms for Prime Factorization and Discrete Logarithms on a Quantum Computer","volume":"26","author":"Shor","year":"1997","journal-title":"SIAM J. Comput."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"5188","DOI":"10.1103\/PhysRevLett.86.5188","article-title":"A One-Way Quantum Computer","volume":"86","author":"Raussendorf","year":"2001","journal-title":"Phys. Rev. Lett."},{"key":"ref_13","unstructured":"Farhi, E., Goldstone, J., Gutmann, S., and Sipser, M. (arXiv, 2000). Quantum Computation by Adiabatic Evolution, arXiv."},{"key":"ref_14","unstructured":"Adachi, S.H., and Henderson, M.P. (arXiv, 2015). Application of Quantum Annealing to Training of Deep Neural Networks, arXiv."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"022308","DOI":"10.1103\/PhysRevA.94.022308","article-title":"Estimation of effective temperatures in quantum annealers for sampling applications: A case study with possible applications in deep learning","volume":"94","author":"Benedetti","year":"2016","journal-title":"Phys. Rev. A"},{"key":"ref_16","unstructured":"Benedetti, M., Realpe-G\u00f3mez, J., Biswas, R., and Perdomo-Ortiz, A. (arXiv, 2016). Quantum-assisted learning of graphical models with arbitrary pairwise connectivity, arXiv."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Terwilliger, A.M., Perdue, G.N., Isele, D., Patton, R.M., and Young, S.R. (2017, January 14\u201319). Vertex Reconstruction of Neutrino Interactions Using Deep Learning. Proceedings of the International Joint Conference on Neural Networks (IJCNN), Anchorage, AK, USA.","DOI":"10.1109\/IJCNN.2017.7966131"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"3241","DOI":"10.1088\/0305-4470\/15\/10\/028","article-title":"On the computational complexity of Ising spin glass models","volume":"15","author":"Barahona","year":"1982","journal-title":"J. Phys. A Math. Gen."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"165","DOI":"10.1007\/BF01343193","article-title":"Beweis des Adiabatensatzes","volume":"51","author":"Born","year":"1928","journal-title":"Z. Phys."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"331","DOI":"10.1007\/s11128-004-7712-7","article-title":"Consistency of the Adiabatic Theorem","volume":"3","author":"Sarandy","year":"2004","journal-title":"Quantum Inf. Process."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"032308","DOI":"10.1103\/PhysRevA.81.032308","article-title":"Necessary condition for the quantum adiabatic approximation","volume":"81","author":"Boixo","year":"2010","journal-title":"Phys. Rev. A"},{"key":"ref_22","unstructured":"Somma, R.D., and Boixo, S. (arXiv, 2011). Spectral Gap Amplification, arXiv."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"024511","DOI":"10.1103\/PhysRevB.82.024511","article-title":"Experimental investigation of an eight-qubit unit cell in a superconducting optimization processor","volume":"82","author":"Harris","year":"2010","journal-title":"Phys. Rev. B"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Choi, V. (arXiv, 2011). Minor-embedding in adiabatic quantum computation: II. Minor-universal graph design, arXiv.","DOI":"10.1007\/s11128-010-0200-3"},{"key":"ref_25","unstructured":"Salakhutdinov, R., and Hinton, G. (2009, January 16\u201318). Deep boltzmann machines. Proceedings of the Artificial Intelligence and Statistics, Beach, FL, USA."},{"key":"ref_26","first-page":"926","article-title":"A practical guide to training restricted Boltzmann machines","volume":"9","author":"Hinton","year":"2010","journal-title":"Momentum"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Diehl, P.U., Neil, D., Binas, J., Cook, M., Liu, S.C., and Pfeiffer, M. (2015, January 12\u201316). Fast-Classifying, High-Accuracy Spiking Deep Networks Through Weight and Threshold Balancing. Proceedings of the International Joint Conference on Neural Networks (IJCNN), Killarney, Ireland.","DOI":"10.1109\/IJCNN.2015.7280696"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Potok, T.E., Schuman, C., Young, S., Patton, R., Spedalieri, F., Liu, J., Yao, K.T., Rose, G., and Chakma, G. (2017, January 30). A Study of Complex Deep Learning Networks on High Performance, Neuromorphic, and Quantum Computers. Proceedings of the Machine Learning in HPC Environments, Salt Lake City, UT, USA.","DOI":"10.1109\/MLHPC.2016.009"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Young, S.R., Rose, D.C., Karnowski, T.P., Lim, S.H., and Patton, R.M. (2015, January 15\u201320). Optimizing Deep Learning Hyper-Parameters Through an Evolutionary Algorithm. Proceedings of the Workshop on Machine Learning in High-Performance Computing Environments, Austin, TX, USA.","DOI":"10.1145\/2834892.2834896"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Young, S.R., Rose, D.C., Johnston, T., Heller, W.T., Karnowski, T.P., Potok, T.E., Patton, R.M., Perdue, G., and Miller, J. (2017, January 12\u201317). Evolving Deep Networks Using HPC. Proceedings of the Machine Learning on HPC Environments, Denver, CO, USA.","DOI":"10.1145\/3146347.3146355"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Sayyaparaju, S., Chakma, G., Amer, S., and Rose, G.S. (2017, January 10\u201312). Circuit Techniques for Online Learning of Memristive Synapses in CMOS-Memristor Neuromorphic Systems. Proceedings of the Great Lakes Symposium on VLSI, Lake Louise, AL, Canada.","DOI":"10.1145\/3060403.3060418"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Liu, C., Yang, Q., Yan, B., Yang, J., Du, X., Zhu, W., Jiang, H., Wu, Q., Barnell, M., and Li, H. (2016, January 11\u201313). A Memristor Crossbar based Computing Engine Optimized for High Speed and Accuracy. Proceedings of the IEEE Computer Society Annual Symposium on VLSI (ISVLSI), Pittsburgh, PA, USA.","DOI":"10.1109\/ISVLSI.2016.46"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Farabet, C., Martini, B., Akselrod, P., Talay, S., LeCun, Y., and Culurciello, E. (June, January 30). Hardware accelerated convolutional neural networks for synthetic vision systems. Proceedings of the 2010 IEEE International Symposium on Circuits and Systems, Vienna, Austria.","DOI":"10.1109\/ISCAS.2010.5537908"},{"key":"ref_34","unstructured":"Yepes, A., Tang, J., and Mashford, B.J. (arXiv, 2017). Improving classification accuracy of feedforward neural networks for spiking neuromorphic chips, arXiv."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Schuman, C.D., Potok, T.E., Young, S., Patton, R., Perdue, G., Chakma, G., Wyer, A., and Rose, G.S. (2018, January 17\u201319). Neuromorphic Computing for Temporal Scientific Data Classification. Proceedings of the Neuromorphic Computing Symposium, Knoxville, TN, USA.","DOI":"10.1145\/3183584.3183612"},{"key":"ref_36","unstructured":"Coates, A., Huval, B., Wang, T., Wu, D.J., Catanzaro, B., and Ng, A.Y. (2013, January 16\u201321). Deep Learning with COTS HPC Systems. Proceedings of the 30th International Conference on Machine Learning (ICML), Atlanta, GA, USA."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Cassidy, A.S., Merolla, P., Arthur, J.V., Esser, S.K., Jackson, B., Alvarez-Icaza, R., Datta, P., Sawada, J., Wong, T.M., and Feldman, V. (2013, January 12\u201317). Cognitive Computing Building Block: A Versatile and Efficient Digital Neuron Model for Neurosynaptic Cores. Proceedings of the International Joint Conference on Neural Networks (IJCNN), Killarney, Ireland.","DOI":"10.1109\/IJCNN.2013.6707077"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s11432-015-5511-7","article-title":"Darwin: A neuromorphic hardware co-processor based on Spiking Neural Networks","volume":"59","author":"Shen","year":"2016","journal-title":"Sci. China Inf. Sci."},{"key":"ref_39","unstructured":"Jouppi, N. (2018, May 17). Google Supercharges Machine Learning Tasks with TPU Custom Chip. Available online: https:\/\/cloudplatform.googleblog.com\/2016\/05\/Google-supercharges-machine-learning-tasks-with-custom-chip.html."},{"key":"ref_40","unstructured":"Nervana (2017, January 30). Nervana Engine. Available online: https:\/\/www.nervanasys.com\/technology\/engine\/."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Comput."},{"key":"ref_42","unstructured":"Esser, S.K., Appuswamy, R., Merolla, P., Arthur, J.V., and Modha, D.S. (2015, January 7\u201312). Backpropagation for energy-efficient neuromorphic computing. Proceedings of the Advances in Neural Information Processing Systems (NIPS), Montr\u00e9al, QC, Canada."},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Arthur, J.V., Merolla, P.A., Akopyan, F., Alvarez, R., Cassidy, A., Chandra, S., Esser, S.K., Imam, N., Risk, W., and Rubin, D.B. (2012, January 10\u201315). Building Block of a Programmable Neuromorphic Substrate: A Digital Neurosynaptic Core. Proceedings of the International Joint Conference on Neural Networks (IJCNN), Brisbane, Australia.","DOI":"10.1109\/IJCNN.2012.6252637"},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1016\/S0925-2312(01)00658-0","article-title":"Error-backpropagation in temporally encoded networks of spiking neurons","volume":"48","author":"Bohte","year":"2002","journal-title":"Neurocomputing"},{"key":"ref_45","unstructured":"Schrauwen, B., and Van Campenhout, J. (2004, January 25\u201329). Extending Spikeprop. Proceedings of the IEEE International Joint Conference on Neural Networks, Budapest, Hungary."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"919","DOI":"10.1038\/78829","article-title":"Competitive Hebbian learning through spike-timing-dependent synaptic plasticity","volume":"3","author":"Song","year":"2000","journal-title":"Nat. Neurosci."},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"28","DOI":"10.1109\/MSPEC.2008.4687366","article-title":"How We Found The Missing Memristor","volume":"45","author":"Williams","year":"2008","journal-title":"IEEE Spectr."},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"1297","DOI":"10.1021\/nl904092h","article-title":"Nanoscale memristor device as synapse in neuromorphic systems","volume":"10","author":"Jo","year":"2010","journal-title":"Nano Lett."},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"389","DOI":"10.1021\/nl203687n","article-title":"A functional hybrid memristor crossbar-array\/CMOS system for data storage and neuromorphic applications","volume":"12","author":"Kim","year":"2011","journal-title":"Nano Lett."},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1038\/nature14441","article-title":"Training and operation of an integrated neuromorphic network based on metal-oxide memristors","volume":"521","author":"Prezioso","year":"2015","journal-title":"Nature"},{"key":"ref_51","doi-asserted-by":"crossref","unstructured":"Schuman, C.D., Plank, J.S., Disney, A., and Reynolds, J. (2016, January 24\u201329). An Evolutionary Optimization Framework for Neural Networks and Neuromorphic Architectures. Proceedings of the International Joint Conference on Neural Networks (IJCNN), Vancouver, BC, USA.","DOI":"10.1109\/IJCNN.2016.7727192"},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"89","DOI":"10.1016\/j.procs.2014.11.089","article-title":"Spatiotemporal Classification Using Neuroscience-Inspired Dynamic Architectures","volume":"41","author":"Schuman","year":"2014","journal-title":"Proc. Comput. Sci."},{"key":"ref_53","unstructured":"Cady, N., Beckmann, K., Manem, H., Dean, M., Rose, G., and Nostrand, J.V. (2016, January 14\u201317). Towards Memristive Dynamic Adaptive Neural Network Arrays. Proceedings of the Government Microcircuit Applications and Critical Technology Conference (GOMACTech), Orlando, FL, USA."},{"key":"ref_54","doi-asserted-by":"crossref","first-page":"232102","DOI":"10.1063\/1.3524521","article-title":"High switching endurance in TaOx memristive devices","volume":"97","author":"Yang","year":"2010","journal-title":"Appl. Phys. Lett."},{"key":"ref_55","doi-asserted-by":"crossref","first-page":"095702","DOI":"10.1088\/0957-4484\/22\/9\/095702","article-title":"Lognormal switching times for titanium dioxide bipolar memristors: origin and resolution","volume":"22","author":"Perner","year":"2011","journal-title":"Nanotechnology"}],"container-title":["Entropy"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1099-4300\/20\/5\/380\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T15:04:51Z","timestamp":1760195091000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1099-4300\/20\/5\/380"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,5,18]]},"references-count":55,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2018,5]]}},"alternative-id":["e20050380"],"URL":"https:\/\/doi.org\/10.3390\/e20050380","relation":{},"ISSN":["1099-4300"],"issn-type":[{"value":"1099-4300","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,5,18]]}}}