Classification Tree Extraction from Trained Artificial Neural Networks

Bondarenko, Andrey; Aļeksejeva, Ludmila; Jumutc, Vilen; Borisov, Arkady

doi:10.1016/j.procs.2017.01.172

Cited by 26 publications

(11 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The rules are generated by examining the possible combinations in the outputs of the discretised network. Similarly, Neural Network Knowledge Extraction (NNKX) [79] produces binary decision trees from multi-layered feed-forward sigmoidal neural networks by grouping the activation values of the last layer and propagating them back to the input to generate clusters. Interval Propagation [30] is an improved version of Validity Interval Analysis (VIA) [80] to extract IF-THEN crisp and fuzzy rules.…”

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

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%

Classification of Explainable Artificial Intelligence Methods through Their Output Formats

Vilone

Longo

2021

MAKE

View full text Add to dashboard Cite

show abstract

“…The rules are extracted by examining the possible combinations in the outputs of the discretised network. Similarly, Neural Network Knowledge eXtraction (NNKX) [238] produces binary decision trees from multi-layered feedforward sigmoidal artificial neural networks by clustering the activation values of the last layer and propagating them back to the input to generate clusters. Interval Propagation [141] is an improved version of Validity Interval Analysis (VIA) [239] to extract IF-THEN crisp and fuzzy rules.…”

Section: Visual Explanations -Miscellaneousmentioning

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

“…The decision tree itself is built using these rules such that the classes (returned by the classifier) are the leaves and the branches represent the sequences of features (conditions) that lead to these classes [1]. Representing the rules in a way which is understandable by human-being is described in [6] and [18].…”

Section: Background and Related Workmentioning

confidence: 99%

Rule Extraction from Neural Networks and Other Classifiers Applied to XSS Detection

Mereani

Howe

2021

Studies in Computational Intelligence

View full text Add to dashboard Cite

Explainable artificial intelligence (XAI) is concerned with creating artificial intelligence that is intelligible and interpretable by humans. Many AI techniques build classifiers, some of which result in intelligible models, some of which don't. Rule extraction from classifiers treated as black boxes is an important topic in XAI, that aims to find rule sets that describe classifiers and that are understandable to humans. Neural networks provide one type of classifier where it is difficult to explain why the inputs map to the decision; support vector machines provide a second example of this kind. A third type of classifier, k-nearest neighbour (k-NN), gives more interpretable classifiers, but suffers from performance problems as the model is little more than a representation of the training data. This work investigates a technique to extract rules from classifiers where the underlying problem's feature space is Boolean, without looking at the inner structure of the classifier. For such a classifier with a small feature space, a Boolean function describing it can be directly calculated, whilst for a classifier with a larger feature space, a sampling method is investigated to produce rulebased approximations to the behaviour of the underlying classifier, with varying granularity, leading to XAI. The behaviour of the technique with neural network, support vector machine, and k-NN classifiers is experimentally assessed on a dataset of cross-site scripting (XSS) attacks, and proves to give very high accuracy and precision, often comparable to the classifier being approximated.

show abstract

Classification Tree Extraction from Trained Artificial Neural Networks

Cited by 26 publications

References 14 publications

Classification of Explainable Artificial Intelligence Methods through Their Output Formats

Classification of Explainable Artificial Intelligence Methods through Their Output Formats

Explainable Artificial Intelligence: a Systematic Review

Rule Extraction from Neural Networks and Other Classifiers Applied to XSS Detection

Contact Info

Product

Resources

About