Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain
the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in
Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles
and JavaScript.
Machine learning with nonlinear optical neural networks
Photonic computing offers many advantages over traditional digital computing, such as high parallelism and low energy consumption, yet current development has been mostly limited to linear operations. In this issue, Hao Wang et al. introduce a large-scale nonlinear photonic neural system based on disordered polycrystalline materials. The system generates both linear and nonlinear optical speckle features, forming a complex neural network that can be used for computing tasks. The authors demonstrate that this nonlinear system provides advantages over linear optical systems for various machine learning tasks, including image classification, regression, and graph classification. The cover image depicts the neural network formed by light scattering through a disordered medium.
As machine learning models are becoming mainstream tools for molecular and materials research, there is an urgent need to improve the nature, quality, and accessibility of atomistic data. In turn, there are opportunities for a new generation of generally applicable datasets and distillable models.
Morphing soft matter, which is capable of changing its shape and function in response to stimuli, has wide-ranging applications in robotics, medicine and biology. Recently, computational models have accelerated its development. Here, we highlight advances and challenges in developing computational techniques, and explore the potential applications enabled by such models.
Dr Kelly Ruggles, associate professor at New York University Langone Health, discusses with Nature Computational Science how she uses computational approaches to gain insights into cancer, inflammation and cardiovascular disease, as well as the importance of mentorship.
A recent study shows that, by leveraging nonlinear optical processes in disordered media, photonic processors can transform high-dimensional machine-learning data, using nonlinear functions that are otherwise challenging for digital electronic processors to compute.
Data about the transition states of rare transitions between long-lived states are needed to simulate physical and chemical processes; however, existing computational approaches often gather little information about these states. A machine-learning technique resolves this challenge by exploiting the century-old theory of committor functions.
While large-scale GPS location datasets have been instrumental to applications in epidemiology, there are still several challenges with these data that should be considered and addressed to make data-driven epidemiology more reliable.
The parallels between natural language and antibody sequences could serve as a stepping stone to using deep language models for analyzing antibody sequences. This Perspective discusses how issues in antibody language model rule mining could be addressed by linguistically formalizing the antibody language.
Nonlinear optical computations have been essential yet challenging for developing optical neural networks with appreciable expressivity. In this paper, light scattering is combined with optical nonlinearity to empower a high-performance, large-scale nonlinear photonic neural system.
The downselection of compounds for synthesis is a key challenge in molecular design cycles that typically relies on expert chemist intuition. Fromer and Coley propose a cost-aware method to automatically select compounds and synthetic routes.
A self-consistent iterative procedure is proposed to compute the committor function for rare events, via a variational principle, and extensively sample the transition state ensemble, allowing for the identification of the relevant variables in the process.