Rodrigo Castellano Ontiveros
Rodrigo Castellano Ontiveros
Marie Skłodowska-Curie Fellow
Research
DeepProofLog: Efficient Proving in Deep Stochastic Logic Programs
A novel NeSy system mapping the resolution process of Deep Stochastic Logic Programs to Markov Decision Processes, enabling efficient Reinforcement Learning for logic proving.
Grounding Methods for Neural-Symbolic AI
Proposes a parameterized family of grounding methods generalizing Backward Chaining to control the trade-off between scalability and expressiveness.
Interpretable Link Prediction via Neural-Symbolic Reasoning
Introduces interpretable-by-design R-CBM-style models that output explicit proof trees, evaluated using XAI metrics like coherence.
Distilling KGE Black Boxes into Interpretable NeSy Models
A framework to distill Knowledge Graph Embeddings into interpretable Neural-Symbolic models, ensuring high fidelity while providing logic proofs.
Constructing Remote Photoplethysmogram Signals
Developed a novel ML methodology that achieved SOTA performance in rPPG signal reconstruction from video, allowing the extraction of different physiological parameters.
Physicochemical modelling of the retention mechanism
Applied Machine Learning algorithms to model the retention mechanisms in HPLC columns.
Evaluating RGB channels in remote photoplethysmography
A comparative study of the efficacy of RGB channels in remote photoplethysmography (rPPG) when compared with contact-based PPG.
Academic
& Industry
Experience
Visiting Researcher
Baker Hughes. Florence, ItalyIntegrating logic reasoning systems with LLM agents.
Visiting Researcher
KU Leuven. Leuven, BelgiumDeveloped DeepProofLog. Collaboration with Ying Jiao, Prof. Giuseppe Marra, and Prof. Luc De Raedt.
Trainee
ING Bank. Brussels, BelgiumInternational Talent Programme. Rotational data science/analytics graduate program.
Master Thesis Researcher
ETH Zürich. Zürich, SwitzerlandrPPG extraction from video. Awarded Karl Engver's Foundation Grant. Supervised by Prof. Carlo Menon and Prof. Moe Elgendi.
Teaching Assistant
KTH Royal Institute of Technology. Stockholm, SwedenSupported courses in Artificial Intelligence (DD2380) and Machine Learning (DD2421).
AI Applied Scientist
Desion, Franunhofer Institute. Darmstadt, GermanyBuilt automated visual inspection systems with Computer Vision models (Mask R-CNN, Faster R-CNN) using synthetic data. Synthetic data created with Unreal Engine.
Education
PhD Researcher in AI
University of Siena. Siena, ItalyMarie Skłodowska-Curie Fellow. Project LeMuR: Learning with Multiple Representations. Supervisors: Prof. Marco Gori, Prof. Michelangelo Diligenti, Dr. Francesco Giannini.
Participation & Dissemination
XAI 2025
Oral: Interpretable Link Prediction via Neural-Symbolic Reasoning
Software
& Code
Free-fall Inspection Systems
Automated visual inspection systems using Computer Vision and synthetic data created with Unreal Engine.
NeSy Grounding
Parametrized grounding methods for scalable neural-symbolic reasoning.
rPPG Construction
Physiological parameters extraction from video using Machine Learning techniques.
Cosmic Rays
Prediction of particles associated to cosmic rays detected by Cherenkov Telescope Array.
Accent Embeddings
Speech technology project focused on accent classification.