Blanca Vargas-Govea

National Institute of Astrophysics, Optics and Electronics

Papers

Total Citations

H-Index

About

Blanca Vargas-Govea is a researcher whose work lies at the intersection of machine learning, relational grammar induction, and action-based sequence analysis. Her primary contributions focus on developing computational models that learn structured, relational grammars from sequences of actions—a foundational challenge in artificial intelligence and robotics. In her most-cited paper, "Learning Relational Grammars from Sequences of Actions" (2009), Vargas-Govea introduced methods for automatically extracting hierarchical, symbolic representations from observed behaviors, enabling systems to understand and generalize complex action patterns. This work, while accruing modest citation counts, has provided a critical framework for researchers exploring how machines can learn from demonstration and reason about procedural knowledge. Her approach bridges symbolic AI and statistical learning, offering insights into how relational structures can be inferred from temporal data. Although her citation impact is still developing, Vargas-Govea’s research is notable for its theoretical depth and its potential applications in human-robot interaction, activity recognition, and cognitive modeling. For students and researchers, her work exemplifies the importance of integrating structure and sequence in machine learning, opening pathways for more interpretable and generalizable AI systems.