Photonic Restricted Boltzmann Machine for Content Generation Tasks

The restricted Boltzmann machine (RBM) is a neural network based on the Ising model, well known for its ability to learn probability distributions and stochastically generate new content. However, the high computational cost of Gibbs sampling in content generation tasks imposes significant bottlenecks on electronic implementations. Here, we propose a photonic restricted Boltzmann machine (PRBM) that leverages photonic computing to accelerate Gibbs sampling, enabling efficient content generation. By introducing an efficient encoding method, the PRBM eliminates the need for computationally intensive matrix decomposition and reduces the computational complexity of a single dot product in Gibbs sampling from O ( N ) to O ( 1 ) . Moreover, with the advantage of photonic computation of non–von Neumann computing architecture, we physically encode the model parameters onto the phases of different wavelength light fields on a spatial light modulator, substantially enhancing computation efficiency for large-scale RBMs. We experimentally validate the photonic-accelerated Gibbs sampling by simulating a two-dimensional Ising model, where the observed phase transition temperature closely matches the theoretical predictions. Beyond physics-inspired tasks, the PRBM demonstrates strong performance in generating and restoring diverse content, including images and temporal sequences. The scalability and reduced training cost of the PRBM framework underscore its potential as a promising pathway for advancing photonic computing in generative artificial intelligence.