ANN-DT : An Algorithm for Extraction of Decision Trees from Artificial Neural Networks

By Madhuri Jha. 2013

Subfields: Safety, Robustness & Interpretability, Program Analysis & Verification

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Safety, Robustness & Interpretability

In Program Analysis & Verification

Citations in the corpus

Explaining Explanations: An Overview of Interpretability of Machine Learning (2018, methodology): “Another decision tree method is ANN-DT [25] which uses sampling to create a decision tree: the key idea is to use sampling to expand training using a nearest neighbor method.”
Rule Extraction Algorithm for Deep Neural Networks: A Review (2016, background): “Schmitz, Aldrich, and Gouws [28] have proposed ANN-DT.”
Explaining Explanations: An Approach to Evaluating Interpretability of Machine Learning (2018, methodology): “‘’ Another decision tree method is ANN-DT [25] which uses sampling to create a decision tree: the key idea is to use sampling to expand training using a nearest neighbor method.”
ForEx++: A New Framework for Knowledge Discovery from Decision Forests (2017, methodology): “Extraction of rules from different types of classifiers is a popular area of research; in recent years a number of rule extraction methods have been proposed (Mashayekhi and Gras (2015), Martens et al. (2008), Schmitz et al. (1999)).”
A Survey on the Explainability of Supervised Machine Learning (2020, methodology): “ANN-DT Interpolated sample outputs Classification Regression Pedagogical Tree-based Schmitz et al. (1999)”
GraphLIME: Local Interpretable Model Explanations for Graph Neural Networks (2020, methodology): “DeepRED [16] was proposed to extract rules from deep neural networks and generate explanations for predictions, and ANN-DT [17] was proposed to extract binary decision trees from neural networks, it is an interpretable model to interpret the main model.”
DeepRED - Rule Extraction from Deep Neural Networks (2016, background): “1023/A%3A1008307919726) Google Scholar (http://scholar.google.com/scholar_lookup? title=FERNN%3A%20an%20algorithm%20for%20fast%20extraction%20of%20 rules%20from%20neural%20networks&author=R.%20Setiono&author=WK.%2 0Leow&journal=Appl.%20Intell.&volume=12&issue=1%E2%80%932&pages=1525&publication_year=”
KDRuleEx: A Novel Approach for Enhancing User Comprehensibility Using Rule Extraction (2012, methodology): “Schmitz et al proposed an pedagogical algorithm, to generate a binary decision tree from the trained network, named as Artificial Neural-Network Decision Tree algorithm (ANN-DT) [7].”
Extended Taxonomy of Rule Extraction Techniques and Assessment of KDRuleEx (2012, unknown): “[19] and ANN-DT[20].”
GNNExplainer: Generating Explanations for Graph Neural Networks (2019, background): “” models with simpler surrogate models, which are then probed for explanations [25, 29, 30].”