Object-Centric Neuro-Argumentative Learning
Jacob, Abdul Rahman, Kori, Avinash, De Angelis, Emanuele, Glocker, Ben, Proietti, Maurizio, Toni, Francesca
–arXiv.org Artificial Intelligence
Over the last decade, as we rely more on deep learning technologies to make critical decisions, concerns regarding their safety, reliability and interpretability have emerged. We introduce a novel Neural Argumentative Learning (NAL) architecture that integrates Assumption-Based Argumentation (ABA) with deep learning for image analysis. Our architecture consists of neural and symbolic components. The former segments and encodes images into facts using object-centric learning, while the latter applies ABA learning to develop ABA frameworks enabling predictions with images. Experiments on synthetic data show that the NAL architecture can be competitive with a state-of-the-art alternative.
arXiv.org Artificial Intelligence
Jun-18-2025
- Country:
- Europe
- Austria > Vienna (0.14)
- Italy > Lazio
- Rome (0.04)
- Spain > Galicia
- A Coruña Province > Santiago de Compostela (0.04)
- United Kingdom > England
- Greater London > London (0.05)
- North America
- South America > Chile
- Europe
- Genre:
- Research Report (0.40)
- Technology: