Concept logic trees: enabling user interaction for transparent image classification and human-in-the-loop learning
Metadata
Show full item recordEditorial
Springer Nature
Materia
Soft decision trees Concepts XAI
Date
2024-02-21Referencia bibliográfica
Rodríguez, D.M., Cuéllar, M.P. & Morales, D.P. Concept logic trees: enabling user interaction for transparent image classification and human-in-the-loop learning. Appl Intell 54, 3667–3679 (2024). https://doi.org/10.1007/s10489-024-05321-4
Sponsorship
HAT.tec GmbH; Funding for open access publishing: Universidad de Granada/CBUA.Abstract
Interpretable deep learning models are increasingly important in domains where transparent decision-making is required. In
this field, the interaction of the user with themodel can contribute to the interpretability of themodel. In this research work, we
present an innovative approach that combines soft decision trees, neural symbolic learning, and concept learning to create an
image classificationmodel that enhances interpretability and user interaction, control, and intervention. The key novelty of our
method relies on the fusion of an interpretable architecture with neural symbolic learning, allowing the incorporation of expert
knowledge and user interaction. Furthermore, our solution facilitates the inspection of the model through queries in the form
of first-order logic predicates. Our main contribution is a human-in-the-loop model as a result of the fusion of neural symbolic
learning and an interpretable architecture.We validate the effectiveness of our approach through comprehensive experimental
results, demonstrating competitive performance on challenging datasets when compared to state-of-the-art solutions.