Learning Fuzzy Relations and Properties for Explainable Artificial Intelligence

Pierrard, Régis; Poli, Jean-Philippe; Hudelot, Céline

doi:10.1109/fuzz-ieee.2018.8491538

Cited by 16 publications

(7 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Four methods based on fuzzy reasoning to generate interpretable sets of rules that show the dependencies between inputs and outputs were presented in [107][108][109][110]. A multiobjective fuzzy Genetics-Based Machine Learning (GBML) algorithm [107] is implemented in the framework of evolutionary multiobjective optimisation (EMO) and consists of a hybrid version of the Michigan and Pittsburgh approaches.…”

Section: Model-specific Xai Methods Based On Neural Networkmentioning

confidence: 99%

“…Finally, it improves interpretability by using regularisation. The fourth method presented in [109] generates fuzzy rules by starting from a set of relations and properties, selected by an expert, of an input dataset. It then extracts the most relevant ones by employing a frequent itemset mining algorithm.…”

Section: Model-specific Xai Methods Based On Neural Networkmentioning

confidence: 99%

See 1 more Smart Citation

Classification of Explainable Artificial Intelligence Methods through Their Output Formats

Vilone

Longo

2021

MAKE

View full text Add to dashboard Cite

Machine and deep learning have proven their utility to generate data-driven models with high accuracy and precision. However, their non-linear, complex structures are often difficult to interpret. Consequently, many scholars have developed a plethora of methods to explain their functioning and the logic of their inferences. This systematic review aimed to organise these methods into a hierarchical classification system that builds upon and extends existing taxonomies by adding a significant dimension—the output formats. The reviewed scientific papers were retrieved by conducting an initial search on Google Scholar with the keywords “explainable artificial intelligence”; “explainable machine learning”; and “interpretable machine learning”. A subsequent iterative search was carried out by checking the bibliography of these articles. The addition of the dimension of the explanation format makes the proposed classification system a practical tool for scholars, supporting them to select the most suitable type of explanation format for the problem at hand. Given the wide variety of challenges faced by researchers, the existing XAI methods provide several solutions to meet the requirements that differ considerably between the users, problems and application fields of artificial intelligence (AI). The task of identifying the most appropriate explanation can be daunting, thus the need for a classification system that helps with the selection of methods. This work concludes by critically identifying the limitations of the formats of explanations and by providing recommendations and possible future research directions on how to build a more generally applicable XAI method. Future work should be flexible enough to meet the many requirements posed by the widespread use of AI in several fields, and the new regulations.

show abstract

Section: Model-specific Xai Methods Based On Neural Networkmentioning

confidence: 99%

Section: Model-specific Xai Methods Based On Neural Networkmentioning

confidence: 99%

Classification of Explainable Artificial Intelligence Methods through Their Output Formats

Vilone

Longo

2021

MAKE

View full text Add to dashboard Cite

show abstract

“…Argumentation-based approaches are believed to have a higher explainability as the notions of arguments and conflictuality are common to the way human reason. Four methods based on fuzzy reasoning to generate interpretable sets of rules that clearly show the dependencies between inputs and outputs were presented in [280,281,282,283]. Both [280,283] examine the interpretability-accuracy tradeoff in fuzzy rule-based classifiers.…”

Section: Model-specific Methods For Explainability Related To Rule-ba...mentioning

confidence: 99%

“…Last, it improves interpretability by using regularization. The method presented in [282] generates fuzzy rules by starting from a set of relations and properties, selected by an expert, of an input dataset. It then extracts the most relevant ones employing a frequent itemset mining algorithm.…”

Section: Model-specific Methods For Explainability Related To Rule-ba...mentioning

confidence: 99%

Explainable Artificial Intelligence: a Systematic Review

Vilone¹,

Longo²

2020

Preprint

View full text Add to dashboard Cite

Explainable Artificial Intelligence (XAI) has experienced a significant growth over the last few years. This is due to the widespread application of machine learning, particularly deep learning, that has led to the development of highly accurate models but lack explainability and interpretability. A plethora of methods to tackle this problem have been proposed, developed and tested. This systematic review contributes to the body of knowledge by clustering these methods with a hierarchical classification system with four main clusters: review articles, theories and notions, methods and their evaluation. It also summarises the state-of-the-art in XAI and recommends future research directions.

show abstract

“…This major shortcoming in the interpretation of a CNN classification mechanism is originates from the black-box nature of such networks. This subject has been recently addressed in several works [16][17][18][19][20][21][22][23][24][25][26][27]. There have been several visualization tools and libraries developed for explaining deep Neural Networks [19,21,22].…”

Section: Explainabilitymentioning

confidence: 99%