Skip to main content
U.S. Department of Energy
Office of Scientific and Technical Information

Adaptive hyperparameter updating for training restricted Boltzmann machines on quantum annealers

Journal Article · · Scientific Reports
 [1];  [2]
  1. Florida A & M Univ.-Florida State Univ., Tallahassee, FL (United States). Dept. of Mechanical Engineering; Florida Center for Advanced Aero-Propulsion (FCAAP), Tallahassee, FL (United States); OSTI
  2. Florida A & M Univ.-Florida State Univ., Tallahassee, FL (United States). Dept. of Mechanical Engineering; Florida Center for Advanced Aero-Propulsion (FCAAP), Tallahassee, FL (United States)

Restricted Boltzmann Machines (RBMs) have been proposed for developing neural networks for a variety of unsupervised machine learning applications such as image recognition, drug discovery, and materials design. The Boltzmann probability distribution is used as a model to identify network parameters by optimizing the likelihood of predicting an output given hidden states trained on available data. Training such networks often requires sampling over a large probability space that must be approximated during gradient based optimization. Quantum annealing has been proposed as a means to search this space more efficiently which has been experimentally investigated on D-Wave hardware. D-Wave implementation requires selection of an effective inverse temperature or hyperparameter (β) within the Boltzmann distribution which can strongly influence optimization. Here, we show how this parameter can be estimated as a hyperparameter applied to D-Wave hardware during neural network training by maximizing the likelihood or minimizing the Shannon entropy. We find both methods improve training RBMs based upon D-Wave hardware experimental validation on an image recognition problem. Neural network image reconstruction errors are evaluated using Bayesian uncertainty analysis which illustrate more than an order magnitude lower image reconstruction error using the maximum likelihood over manually optimizing the hyperparameter. The maximum likelihood method is also shown to out-perform minimizing the Shannon entropy for image reconstruction.

Research Organization:
Florida A & M Univ.-Florida State Univ., Tallahassee, FL (United States)
Sponsoring Organization:
USDOE Office of Science (SC), Basic Energy Sciences (BES). Scientific User Facilities Division
Grant/Contract Number:
AC05-00OR22725
OSTI ID:
1816563
Journal Information:
Scientific Reports, Journal Name: Scientific Reports Journal Issue: 1 Vol. 11; ISSN 2045-2322
Publisher:
Nature Publishing GroupCopyright Statement
Country of Publication:
United States
Language:
English

References (11)

DRAM: Efficient adaptive MCMC journal December 2006
Quantum machine learning journal September 2017
Temperature based Restricted Boltzmann Machines journal January 2016
Limitations of error corrected quantum annealing in improving the performance of Boltzmann machines journal August 2020
Robustness of adiabatic quantum computation journal December 2001
Searching for quantum speedup in quasistatic quantum annealers journal November 2015
Power of Pausing: Advancing Understanding of Thermalization in Experimental Quantum Annealers journal April 2019
Thermalization, Freeze-out, and Noise: Deciphering Experimental Quantum Annealers journal December 2017
Learnability scaling of quantum states: Restricted Boltzmann machines journal November 2019
Quantum-Assisted Learning of Hardware-Embedded Probabilistic Graphical Models journal November 2017
Training Products of Experts by Minimizing Contrastive Divergence journal August 2002

Similar Records

Training Restricted Boltzmann Machines With a D-Wave Quantum Annealer
Journal Article · Tue Jun 29 00:00:00 EDT 2021 · Frontiers in Physics · OSTI ID:1804128

Restricted Boltzmann Machines for galaxy morphology classification with a quantum annealer
Journal Article · Wed Nov 13 23:00:00 EST 2019 · TBD · OSTI ID:1594136

Related Subjects