Probabilistic Photonic Computing

TL;DR

Probabilistic photonic computing leverages physical properties of light to create low-latency, energy-efficient systems for AI and uncertainty modeling, overcoming limitations of traditional deterministic hardware.

Contribution

This paper reviews key developments in physical photonic computing and photonic random number generation, proposing their potential for probabilistic processors in AI.

Findings

Photonic systems enable inherent probabilistic architectures.

Photonic random number generators provide high-quality entropy sources.

Potential for integration with AI systems for low-latency processing.

Abstract

Probabilistic computing excels in approximating combinatorial problems and modelling uncertainty. However, using conventional deterministic hardware for probabilistic models is challenging: (pseudo) random number generation introduces computational overhead and additional data shuffling, which is particularly detrimental for safety-critical applications requiring low latency such as autonomous driving. Therefore, there is a pressing need for innovative probabilistic computing architectures that achieve low latencies with reasonable energy consumption. Physical computing offers a promising solution, as these systems do not rely on an abstract deterministic representation of data but directly encode the information in physical quantities. Therefore, they can be seamlessly integrated with physical entropy sources, enabling inherent probabilistic architectures. Photonic computing is a prominent variant due to the large available bandwidth, several orthogonal degrees of freedom for data encoding and optimal properties for in-memory computing and parallel data transfer. Here, we highlight key developments in physical photonic computing and photonic random number generation. We provide insights into the realization of probabilistic photonic processors and lend our perspective on their impact on AI systems and future challenges.