A new training interface allows a robot to learn a task in several different ways. This increased training flexibility could help more people interact with and teach robots — and may also enable robots to learn a wider set of skills.

Researchers from the University of Tokyo in collaboration with Aisin Corporation have demonstrated that universal scaling laws, which describe how the properties of a system change with size and scale, apply to deep neural networks that exhibit absorbing phase transition behavior, a phenomenon typically observed in physical systems. The discovery not only provides a framework describing deep neural networks but also helps predict their trainability or generalizability. The findings were published in the journal Physical Review Research.

The R package rcssci offers an intuitive solution for visualizing Restricted Cubic Splines (RCS) in regression analyses. It automates the generation of spline plots for outcomes like odds ratios (OR), hazard ratios (HR), and risk ratios (RR), facilitating the identification of non-linear relationships in data. Supporting Cox, Logistic, linear, and quasi-Poisson models, rcssci aids researchers in interpreting complex data relationships before delving into advanced machine learning techniques.

Through large-scale cohort analysis, researchers have established a novel and stable classification of sepsis patients. Multi-machine learning integrated prognostic models prove highly effective in identifying high-risk C3 subtype patients, offering significant clinical utility. ELL2 derived from B cells as a potential new biomarker for prognosis prediction and diagnostic differentiation in sepsis patients.

A task force formed at the Banbury Center has issued a report on cognition and behavior in the genetic disease NF1. The group proposes a new research framework that could lead to earlier detection and more personalized care.

Achieving high efficiency, long operational lifetime, and excellent color purity is essential for organic light-emitting diode (OLED) materials used in next-generation display and lighting technologies, but these performance goals are increasingly difficult to reach with conventional trial-and-error design methods. In a new review published in Science Bulletin, researchers from Beijing Jiaotong University and Sichuan University present "Integrating AI into OLED Material Design: A Comprehensive Review of Computational Frameworks, Challenges, and Opportunities." The paper discusses how artificial intelligence (AI) can help overcome the limitations of traditional approaches, accelerate OLED material discovery, and offers a practical multi-level framework to guide future research in this field.