Artificial intelligence (AI) promises to reshape scientific inquiry and enable breakthrough discoveries in areas such as energy storage, quantum computing, and biomedicine. Scanning transmission electron microscopy (STEM), a cornerstone of the study of chemical and materials systems, stands to benefit greatly from AI-driven automation. However, present barriers to low-level instrument control, as well as generalizable and interpretable feature detection, make truly automated microscopy impractical. Here, we discuss the design of a closed-loop instrument control platform guided by emerging sparse data analytics. We hypothesize that a centralized controller, informed by machine learning combining limited a priori knowledge and task-based discrimination, could drive on-the-fly experimental decision-making. This platform may unlock practical, automated analysis of a variety of material features, enabling new high-throughput and statistical studies.

A series of editorials in this Journal have argued that psychiatry is in the midst of a crisis. The various solutions proposed would all involve a strengthening of psychiatry's identity as essentially ‘applied neuroscience’. Although not discounting the importance of the brain sciences and psychopharmacology, we argue that psychiatry needs to move beyond the dominance of the current, technological paradigm. This would be more in keeping with the evidence about how positive outcomes are achieved and could also serve to foster more meaningful collaboration with the growing service user movement.