Quantum Semantic Learning by Reverse Annealing of an Adiabatic Quantum Computer. Issue 2 (14th December 2020)

• Record Type: Journal Article
• Authors: Rocutto, Lorenzo; Destri, Claudio; Prati, Enrico
• Is Part Of: Advanced quantum technologies. Volume 4:Issue 2(2021)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2020-12-14
• Subjects: adiabatic quantum computer -- Boltzmann machine -- reverse annealing -- semantic learning; Quantum theory -- Periodicals; Quantum computing -- Periodicals; Quantum chemistry -- Periodicals; Quantum electronics -- Periodicals; 537.5
• DOI: 10.1002/qute.202000133
• Languages: English
• ISSNs: 2511-9044

Abstract

Abstract: Restricted Boltzmann machines (RBMs) constitute a class of neural networks for unsupervised learning with applications ranging from pattern classification to quantum state reconstruction. Despite the potential representative power, the diffusion of RBMs is quite limited since their training process proves to be hard. The advent of commercial adiabatic quantum computers (AQCs) raised the expectation that the implementations of RBMs on such quantum devices can increase the training speed with respect to conventional hardware. Here, the feasibility of a complete RBM on AQCs is demonstrated, thanks to an embedding that associates the nodes of the neural networks to virtual qubits. A semantic quantum search is implemented thanks to a reverse annealing schedule. Such an approach exploits more information from the training data, mimicking the behavior of the classical Gibbs sampling algorithm. The semantic training is shown to quickly raise the sampling probability of a subset of the set of the configurations. Even without a proper optimization of the annealing schedule, the RBM semantically trained achieves good scores on reconstruction tasks. The development of such techniques paves the way toward the establishment of a quantum advantage of adiabatic quantum computers, especially given the foreseen improvement of such hardware. Abstract : A complete restricted Boltzmann machine is implemented on an adiabatic quantum computer, by an embedding that associates the nodes of the neural network to virtual qubits. A semantic quantum search is cast in the adiabatic quantum computers by reverse annealing schedule. Such an approach exploits more information from the training data, mimicking the behavior of the classical Gibbs sampling algorithm.