Hybrid Helmholtz machines
| Autor: | Frank Phillipson, Niels M. P. Neumann, Teresa J. van Dam, Hans van den Berg |
|---|---|
| Přispěvatelé: | Centrum Wiskunde & Informatica, Amsterdam (CWI), The Netherlands, Design and Analysis of Communication Systems |
| Jazyk: | angličtina |
| Rok vydání: | 2020 |
| Předmět: |
Quantum machine learning
Computer science 01 natural sciences 010305 fluids & plasmas Theoretical Computer Science Quantum circuit symbols.namesake Helmholtz machine 0103 physical sciences Machine learning Electrical and Electronic Engineering 010306 general physics Quantum Quantum computer Gate-based quantum computing Artificial neural network 22/2 OA procedure Bayesian network Statistical and Nonlinear Physics Quantum computing Electronic Optical and Magnetic Materials Computer engineering Modeling and Simulation Helmholtz free energy Signal Processing symbols Hybrid algorithms |
| Zdroj: | Quantum Information Processing, 19(6) Quantum Information Processing, 19(6):174. Springer Quantum Information Processing, 19(6):174. Springer Verlag |
| ISSN: | 1573-1332 1570-0755 |
| Popis: | Quantum machine learning has the potential to overcome problems that current classical machine learning algorithms face, such as large data requirements or long learning times. Sampling is one of the aspects of classical machine learning that might benefit from quantum machine learning, as quantum computers intrinsically excel at sampling. Current hybrid quantum-classical implementations provide ways to already use near-term quantum computers for practical applications. By expanding the horizon on hybrid quantum-classical approaches, this work proposes the first implementation of a gated quantum-classical hybrid Helmholtz machine, a gate-based quantum circuit approximation of a neural network for unsupervised tasks. Our approach focuses on parameterized shallow quantum circuits and effectively implements an approximate Bayesian network, overcoming the exponential complexity of exact networks. In addition, a new balanced cost function is introduced, preventing the need of millions of training samples. Using a bars and stripes data set, the model, implemented on the Quantum Inspire platform, is shown to outperform classical Helmholtz machines in terms of the Kullback–Leibler divergence. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full text from SpringerLink