A hybrid quantum enabled RBM advantage: convolutional autoencoders for quantum image compression and generative learning

dc.contributor.authorSleeman, Jennifer
dc.contributor.authorDorband, John
dc.contributor.authorHalem, Milton
dc.date.accessioned2020-07-22T16:22:44Z
dc.date.available2020-07-22T16:22:44Z
dc.date.issued2020-05-20
dc.description.abstractUnderstanding how the D-Wave quantum computer could be used for machine learning problems is of growing interest. Our work explores the feasibility of using the D-Wave as a sampler for a machine learning task. We describe a hybrid method that combines a classical deep neural network autoencoder with a quantum annealing Restricted Boltzmann Machine (RBM) using the D-Wave for image generation. Our method overcomes two key limitations in the 2000-qubit D-Wave processor, namely the limited number of qubits available to accommodate typical problem sizes for fully connected quantum objective functions, and samples that are binary pixel representations. As a consequence of these limitations we are able to show how we achieved nearly a 22-fold compression factor of grayscale 28 x 28 sized images to binary 6 x 6 sized images with a lossy recovery of the original 28 x 28 grayscale images. We further show how generating samples from the D-Wave after training the RBM, resulted in 28 x 28 images that were variations of the original input data distribution, as opposed to recreating the training samples. We evaluated the quality of this method by using a downstream classification method. We formulated a MNIST classification problem using a deep convolutional neural network that used samples from the quantum RBM to train the MNIST classifier and compared the results with a MNIST classifier trained with the original MNIST training data set, as well as a MNIST classifier trained using classical RBM samples. We also explored using a secondary dataset, the MNIST Fashion dataset and demonstrate the first quantum-generated fashion. Our hybrid autoencoder approach indicates advantage for RBM results relative to the use of a current RBM classical computer implementation for image-based machine learning and even more promising results for the next generation D-Wave quantum system. Our method for compression and image mappings is not constrained to RBMs, the autoencoder part of this method could be coupled with other quantum-based algorithms.en_US
dc.description.sponsorshipThis work was supported by D-Wave for system access and support as member in NSF-funded CHMPR, and through the NASA grant for Quantum, grant number #NNH16ZDA001N-AIST16-0091.en_US
dc.description.urihttps://www.spiedigitallibrary.org/conference-proceedings-of-spie/11391/2558832/A-hybrid-quantum-enabled-RBM-advantage--convolutional-autoencoders-for/10.1117/12.2558832.shorten_US
dc.format.extent17 pagesen_US
dc.genreconference papers and proceedingsen_US
dc.identifierdoi:10.13016/m256rj-nyji
dc.identifier.citationJennifer Sleeman, John Dorband, and Milton Halem "A hybrid quantum enabled RBM advantage: convolutional autoencoders for quantum image compression and generative learning", Proc. SPIE 11391, Quantum Information Science, Sensing, and Computation XII, 113910B (20 May 2020); https://doi.org/10.1117/12.2558832en_US
dc.identifier.urihttps://doi.org/10.1117/12.2558832
dc.identifier.urihttp://hdl.handle.net/11603/19215
dc.language.isoen_USen_US
dc.publisherSPIEen_US
dc.relation.isAvailableAtThe University of Maryland, Baltimore County (UMBC)
dc.relation.ispartofUMBC Computer Science and Electrical Engineering Department Collection
dc.relation.ispartofUMBC Faculty Collection
dc.relation.ispartofUMBC Student Collection
dc.rightsThis item is likely protected under Title 17 of the U.S. Copyright Law. Unless on a Creative Commons license, for uses protected by Copyright Law, contact the copyright holder or the author.
dc.rights©2020 Society of Photo-Optical Instrumentation Engineers (SPIE). One print or electronic copy may be made for personal use only. Systematic reproduction and distribution, duplication of any material in this paper for a fee or for commercial purposes, or modification of the content of the paper are prohibited.
dc.subjectUMBC Ebiquity Research Group
dc.titleA hybrid quantum enabled RBM advantage: convolutional autoencoders for quantum image compression and generative learningen_US
dc.typeTexten_US

Files

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
113910B.pdf
Size:
1.54 MB
Format:
Adobe Portable Document Format
Description:

License bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
license.txt
Size:
2.56 KB
Format:
Item-specific license agreed upon to submission
Description: