Towards Explainable Neural-Symbolic Visual Reasoning
By Adrien Bennetot, Jean Luc Laurent, Raja Chatila, Natalia Díaz Rodríguez. 2019
47 citations recorded by the source corpus.
Subfields: Computer Vision and Pattern Recognition, Safety, Robustness & Interpretability
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
- Salvador Garcia
- Francisco Herrera
- Adrien Bennetot
- Alejandro Barredo Arrieta
- Sergio Gil-Lopez
- Ala Al-Fuqaha
- Daniel Molina
- Khansa Rasheed
In Safety, Robustness & Interpretability
- Adrien Bennetot
- Elena Hernández-Pereira
- Eduardo Mosqueira-Rey
- Á. Fernández-Leal
- José Bobes-Bascarán
- David Alonso-Ríos
- Ala Al-Fuqaha
- Khansa Rasheed
Citations in the corpus
- Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI (2019, positive): “Having a semantic representation of the knowledge can help a model to have the ability to produce explanations (e.g., in natural language [169] ) combining common sense reasoning and human-understandable features.”
- Explainable, trustworthy, and ethical machine learning for healthcare: A survey (2021, background): “Thus, the explanation provides a fair analysis of model architecture and learned parameters [42].”
- Human-in-the-loop machine learning: a state of the art (2022, methodology): “In particular, this can be done by constraining the neural network thanks to a semantic KB and bias-prone concepts (Bennetot et al. 2019), or by stacking ensembles jointly encompassing white and black-box models (Loyola-González 2019).”