Restricted Boltzmann machine based on a Fermi sea

In recent years, there has been an intensive research on how to exploit the quantum laws of nature in the machine learning. Models have been put forward which employ spins, photons, and cold atoms. In this work we study the possibility of using the lattice fermions to learn the classical data. We propose an alternative to the quantum Boltzmann machine, the so-called spin-fermion machine (SFM), in which the spins represent the degrees of freedom of the observable data (to be learned), and the fermions represent the correlations between the data. The coupling is linear in spins and quadratic in fermions. The fermions are allowed to tunnel between the lattice sites. The training of SFM can be efficiently implemented since there are closed expressions for the log-likelihood gradient. We find that SFM is more powerful than the classical restricted Boltzmann machine with the same number of physical degrees of freedom. The reason is that SFM has additional freedom due to the rotation of the Fermi sea. We show examples for several data sets.

Automated summary

Recent research focuses on leveraging the quantum laws of nature in machine learning, with models such as the spin-fermion machine proposed. SFM training is efficient with closed expressions for the log-likelihood gradient, showing greater power compared to classical models.