Brückerhoff-Plückelmann Frank, Borras Hendrik, Klein Bernhard, Varri Akhil, Becker Marlon, Dijkstra Jelle, Brückerhoff Martin, Wright C David, Salinga Martin, Bhaskaran Harish, Risse Benjamin, Fröning Holger, Pernice Wolfram
Physical Institute, University of Münster, Münster, 48149, Germany.
Kirchhoff-Institute for Physics, University of Heidelberg, Heidelberg, 69120, Germany.
Nat Commun. 2024 Dec 1;15(1):10445. doi: 10.1038/s41467-024-54931-6.
Biological neural networks effortlessly tackle complex computational problems and excel at predicting outcomes from noisy, incomplete data. Artificial neural networks (ANNs), inspired by these biological counterparts, have emerged as powerful tools for deciphering intricate data patterns and making predictions. However, conventional ANNs can be viewed as "point estimates" that do not capture the uncertainty of prediction, which is an inherently probabilistic process. In contrast, treating an ANN as a probabilistic model derived via Bayesian inference poses significant challenges for conventional deterministic computing architectures. Here, we use chaotic light in combination with incoherent photonic data processing to enable high-speed probabilistic computation and uncertainty quantification. We exploit the photonic probabilistic architecture to simultaneously perform image classification and uncertainty prediction via a Bayesian neural network. Our prototype demonstrates the seamless cointegration of a physical entropy source and a computational architecture that enables ultrafast probabilistic computation by parallel sampling.
生物神经网络能够轻松解决复杂的计算问题，并且擅长从噪声大、不完整的数据中预测结果。受这些生物神经网络启发的人工神经网络（ANN）已成为用于解读复杂数据模式和进行预测的强大工具。然而，传统的人工神经网络可被视为“点估计”，无法捕捉预测的不确定性，而预测本质上是一个概率性过程。相比之下，将人工神经网络视为通过贝叶斯推理得出的概率模型，对传统的确定性计算架构构成了重大挑战。在此，我们将混沌光与非相干光子数据处理相结合，以实现高速概率计算和不确定性量化。我们利用光子概率架构，通过贝叶斯神经网络同时进行图像分类和不确定性预测。我们的原型展示了物理熵源与计算架构的无缝融合，该架构通过并行采样实现超快速概率计算。
