Miha Ravber

Papers

Total Citations

H-Index

About

Miha Ravber is a computer scientist whose research bridges the frontiers of grammar inference, semantic inference, and evolutionary computation. His most influential work, "From Grammar Inference to Semantic Inference—An Evolutionary Approach" (2020, 15 citations), introduces a paradigm-shifting extension of traditional grammar induction. While Grammar Inference traditionally focuses on deriving syntactic structures from program samples, Ravber’s pioneering approach advances the field by enabling machines to infer not just form, but meaning—extracting semantic rules from positive and negative examples. This evolutionary methodology has opened new pathways for automated program understanding and synthesis. Beyond this cornerstone paper, Ravber’s broader contributions lie in developing computational models that learn both structure and function, with applications in software engineering and artificial intelligence. His work has been recognized for its conceptual depth and practical potential, earning citations from researchers in evolutionary computation and machine learning. For students and scholars exploring the intersection of program induction and evolutionary algorithms, Ravber’s research offers a compelling vision: teaching computers to learn not just the grammar of code, but the semantics of intent.