Communications of the ACM
FSU Researchers Enhance Quantum Machine Learning Algorithms
FSU's William Oates (left) and Guanglei Xu applied Restricted Boltzmann Machines for machine learning to support hyperparameter optimization.
Credit: Florida State University
Florida State University Professor William Oates and postdoctoral researcher Guanglei Xu found a way to automatically infer parameters used in an important quantum Boltzmann machine algorithm for machine learning applications.
They describe their findings in "Adaptive Hyperparameter Updating for Training Restricted Boltzmann Machines on Quantum Annealers," published in Scientific Reports.
The work could help build artificial neural networks that could be used for training computers to solve complicated, interconnected problems.
One way to build neural networks is by using a restricted Boltzmann machine, an algorithm that uses probability to learn based on inputs given to the network. Oates and Xu found a way to automatically calculate an important parameter associated with effective temperature that is used in that algorithm.
From Florida State University
View Full Article
No entries found