Learning Enabled

Learning-enabled systems, which integrate machine learning (ML) into software and hardware, are rapidly expanding across various domains, but their development and deployment present unique engineering challenges. Current research focuses on improving the reliability and safety of these systems, addressing issues such as robust testing and evaluation methodologies across the entire system lifecycle, and developing frameworks for ensuring safety and adaptability in dynamic, constrained environments. This work is crucial for building trust and enabling the wider adoption of ML-powered technologies in safety-critical applications like autonomous vehicles and healthcare, ultimately impacting both the scientific understanding of AI and its practical implementation.