Photonic restricted Boltzmann machine for content generation tasks
By: Li Luo , Yisheng Fang , Wanyi Zhang and more
Potential Business Impact:
Makes AI create pictures and sounds faster.
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 Gibbs sampling from $O(N)$ to $O(1)$. Moreover, its non-Von Neumann photonic computing architecture circumvents the memory storage of interaction matrices, providing substantial advantages 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 robust capabilities in generating and restoring diverse content, including images and temporal sequences, even in the presence of noise and aberrations. 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.
Similar Papers
The Gaussian-Multinoulli Restricted Boltzmann Machine: A Potts Model Extension of the GRBM
Machine Learning (CS)
Teaches computers to remember and reason better.
Generative modeling using evolved quantum Boltzmann machines
Quantum Physics
Teaches quantum computers to learn hard patterns.
The unbearable lightness of Restricted Boltzmann Machines: Theoretical Insights and Biological Applications
Disordered Systems and Neural Networks
Helps computers learn from data better.