In this HDS‑LEE project, we will use machine learning (ML) along with data from previously solved problem instances to solve new, yet similar, instances more efficiently than with general purpose algorithms such as Newton's method. * Become familiar with our previously developed neural network superstructure for learning iterative algorithms * Explore hybrid ML-classical approaches, the application of meta learning, and the integration of convex optimization layers * Strong background in numerical methods and machine learning * Unique HDS-LEE graduate school program (including data science courses, soft skill courses and annual retreats) Further development of your personal strengths, e. g., via a comprehensive further training program; a structured program of continuing education and networking opportunities specifically for doctoral researchers via JuDocS, the ...
mehr