Training Restricted Boltzmann Machines With a D-Wave Quantum Annealer
Restricted Boltzmann Machine (RBM) is an energy-based, undirected graphical model. It is commonly used for unsupervised and supervised machine learning. Typically, RBM is trained using contrastive divergence (CD). However, training with CD is slow and does not estimate the exact gradient of the log-...
Main Authors: | Vivek Dixit, Raja Selvarajan, Muhammad A. Alam, Travis S. Humble, Sabre Kais |
---|---|
Format: | Article |
Language: | English |
Published: |
Frontiers Media S.A.
2021-06-01
|
Series: | Frontiers in Physics |
Subjects: | |
Online Access: | https://www.frontiersin.org/articles/10.3389/fphy.2021.589626/full |
Similar Items
-
Prime factorization using quantum variational imaginary time evolution
by: Raja Selvarajan, et al.
Published: (2021-10-01) -
Dimensionality Reduction with Variational Encoders Based on Subsystem Purification
by: Raja Selvarajan, et al.
Published: (2023-11-01) -
Variational Quantum Circuits to Prepare Low Energy Symmetry States
by: Raja Selvarajan, et al.
Published: (2022-02-01) -
Finite-Size Scaling on a Digital Quantum Simulator Using Quantum Restricted Boltzmann Machine
by: Bilal Khalid, et al.
Published: (2022-05-01) -
A universal quantum circuit design for periodical functions
by: Junxu Li, et al.
Published: (2021-01-01)