Skip to Main content Skip to Navigation
Theses

Explainable Classification and Annotation through Relation Learning and Reasoning

Abstract : With the recent successes of deep learning and the growing interactions between humans and AIs, explainability issues have risen. Indeed, it is difficult to understand the behaviour of deep neural networks and thus such opaque models are not suited for high-stake applications. In this thesis, we propose an approach for performing classification or annotation and providing explanations. It is based on a transparent model, whose reasoning is clear, and on interpretable fuzzy relations that enable to express the vagueness of natural language.Instead of learning on training instances that are annotated with relations, we propose to rely on a set of relations that was set beforehand. We present two heuristics that make the process of evaluating relations faster. Then, the most relevant relations can be extracted using a new fuzzy frequent itemset mining algorithm. These relations enable to build rules, for classification, and constraints, for annotation. Since the strengths of our approach are the transparency of the model and the interpretability of the relations, an explanation in natural language can be generated.We present experiments on images and time series that show the genericity of the approach. In particular, the application to explainable organ annotation was received positively by a set of participants that judges the explanations consistent and convincing.
Document type :
Theses
Complete list of metadata

https://tel.archives-ouvertes.fr/tel-03115438
Contributor : Abes Star :  Contact
Submitted on : Tuesday, January 19, 2021 - 4:23:26 PM
Last modification on : Saturday, May 1, 2021 - 3:49:35 AM
Long-term archiving on: : Tuesday, April 20, 2021 - 7:49:51 PM

File

86491_PIERRARD_2020_archivage....
Version validated by the jury (STAR)

Identifiers

  • HAL Id : tel-03115438, version 1

Citation

Régis Pierrard. Explainable Classification and Annotation through Relation Learning and Reasoning. Artificial Intelligence [cs.AI]. Université Paris-Saclay, 2020. English. ⟨NNT : 2020UPAST008⟩. ⟨tel-03115438⟩

Share

Metrics

Record views

162

Files downloads

179