Rolf Morel

Papers

Total Citations

H-Index

About

Rolf Morel is a rising star in the field of inductive logic programming (ILP), with a focus on pushing the boundaries of program learning. His key research areas include higher-order logic program synthesis and the development of robust learning frameworks for symbolic AI. Morel's most notable contribution is his pioneering work on learning higher-order logic programs, which significantly expands the expressive power of ILP beyond traditional first-order approaches. His 2019 paper on this topic, which has garnered 6 citations, introduced novel techniques extending meta-interpretive learning to handle higher-order constructs. Morel further advanced the field with his 2021 work on "learning from failures," a paradigm-shifting approach that decomposes ILP into generate, test, and constrain stages. This method, which has already attracted 3 citations, offers a more principled and efficient way to navigate the hypothesis space by systematically learning from incorrect candidates. Morel's work is particularly impactful for researchers interested in automated program synthesis, AI reasoning, and the intersection of symbolic and statistical learning. His contributions are laying the groundwork for more powerful and flexible machine learning systems capable of discovering complex, recursive programs from minimal data.