Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

Computational Methods in Science and Technology

Applying a Quantum Annealing Based Restricted Boltzmann Machine for MNIST Handwritten Digit Classification

Krzysztof Kurowski, Slysz, M., Subocz, M., Różycki, R.

Published Jul 2, 2021• 9 citations
Publisher
DOI
10.12921/cmst.2021.0000011

Related papers

Improved error tolerance of programmable photonic integrated circuits for MNIST handwritten digit classification

Juan Zhang, Zhiyuan Wu, Yang Wang

Optics & Laser Technology•Sep 22, 2023•6 citations

Revisiting Quantum Neural Networks for Handwritten-Digit Classification: A Reproducible Study with a Closed-Form and Ceiling Analysis

Tee Hui Teo

•Jan 1, 2026•0 citations

Evaluating the Advantage 2 Quantum Annealer Prototype: A Comparative Evaluation with Advantage 1 and Hybrid Solver and Classical Restricted Boltzmann Machines on MNIST Classification

Hadi Salloum, Laith Nayal, Manuel Mazzara

Springer proceedings in mathematics & statistics•Jul 16, 2025•0 citations

Quantum Neural Network in Recognition of Handwritten Numerals

Jie Zhou, QIANG GAN, Adam Krzyżak +1 more

Series in machine perception and artificial intelligence•Jun 1, 1999•6 citations

Towards Sampling from Nondirected Probabilistic Graphical models using a D-Wave Quantum Annealer

Yaroslav Koshka, M. A. Novotny

A D-Wave quantum annealer (QA) having a 2048 qubit lattice, with no missing qubits and couplings, allowed embedding of a complete graph of a Restricted Boltzmann Machine (RBM). A handwritten digit OptDigits data set having 8x7 pixels of visible units was used to train the RBM using a classical Contrastive Divergence. Embedding of the classically-trained RBM into the D-Wave lattice was used to demonstrate that the QA offers a high-efficiency alternative to the classical Markov Chain Monte Carlo (MCMC) for reconstructing missing labels of the test images as well as a generative model. At any training iteration, the D-Wave-based classification had classification error more than two times lower than MCMC. The main goal of this study was to investigate the quality of the sample from the RBM model distribution and its comparison to a classical MCMC sample. For the OptDigits dataset, the states in the D-Wave sample belonged to about two times more local valleys compared to the MCMC sample. All the lowest-energy (the highest joint probability) local minima in the MCMC sample were also found by the D-Wave. The D-Wave missed many of the higher-energy local valleys, while finding many "new" local valleys consistently missed by the MCMC. It was established that the "new" local valleys that the D-Wave finds are important for the model distribution in terms of the energy of the corresponding local minima, the width of the local valleys, and the height of the escape barrier.

arXiv:1905.00159•May 1, 2019•2 citations

Novel Exotic Projected Quantum Kernel Features-Enabled Neural Network for Handwritten Digit Image Classification

M. Shyamala Devi, J. Arun Pandian, P. S. Ramesh +4 more

Lecture notes in networks and systems•Nov 24, 2022•0 citations
A D-Wave quantum annealer (QA) having a 2048 qubit lattice, with no missing qubits and couplings, allowed embedding of a complete graph of a Restricted Boltzmann Machine (RBM). A handwritten digit OptDigits data set having 8x7 pixels of visible units was used to train the RBM using a classical Contrastive Divergence. Embedding of the classically-trained RBM into the D-Wave lattice was used to demonstrate that the QA offers a high-efficiency alternative to the classical Markov Chain Monte Carlo (MCMC) for reconstructing missing labels of the test images as well as a generative model. At any training iteration, the D-Wave-based classification had classification error more than two times lower than MCMC. The main goal of this study was to investigate the quality of the sample from the RBM model distribution and its comparison to a classical MCMC sample. For the OptDigits dataset, the states in the D-Wave sample belonged to about two times more local valleys compared to the MCMC sample. All the lowest-energy (the highest joint probability) local minima in the MCMC sample were also found by the D-Wave. The D-Wave missed many of the higher-energy local valleys, while finding many "new" local valleys consistently missed by the MCMC. It was established that the "new" local valleys that the D-Wave finds are important for the model distribution in terms of the energy of the corresponding local minima, the width of the local valleys, and the height of the escape barrier.