Reverse Engineering the Neural Networks for Rule Extraction in Classification Problems

By Gethsiyal Augasta M, Thangairulappan Kathirvalavakumar. 2012

180 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computational Theory and Mathematics, Control and Systems Engineering, 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 Artificial Intelligence

In Computational Theory and Mathematics

In Control and Systems Engineering

In Safety, Robustness & Interpretability

Citations in the corpus

Explaining Explanations: An Overview of Interpretability of Machine Learning (2018, methodology): “DeepRED utilizes several strategies to simplify its decision trees: it uses RxREN [23] to prune unnecessary input, and it applies algorithm C4.”
Local Rule-Based Explanations of Black Box Decision Systems (2018, background): “Classification rules have been widely used to explain neural networks [2, 3, 21] but also to understand the global behavior of SVMs [15, 27].”
Rule Extraction Algorithm for Deep Neural Networks: A Review (2016, methodology): “A reverse engineering approach algorithm called RxREN which is proposed by Augusta and Kathirvalavakumar [27] extracts an IF-THEN rule from a neural network.”
Meaningful Explanations of Black Box AI Decision Systems (2019, neutral): “…Sivakumar, and Bhattacharya 1999) and tree ensembles (Tan, Hooker, and Wells 2016), while decision rules have been widely used to explain neural networks (Augasta and Kathirvalavakumar 2012; Andrews, Diederich, and Tickle 1995) and SVM (Support Vector Machines) (Fung, Sandilya, and Rao 2005).”
DeepRED - Rule Extraction from Deep Neural Networks (2016, methodology): “The works dealing with pedagogical rule extraction, for instance, comprise the VIA method discussed in [17, 18], different sampling-based approaches [5, 16, 13, 21, 14], and the RxREN algorithm [2].”
Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI (2019, unknown): “• Some methods [82, 144] are classified on a single category (Explanation by simplification for MultiLayer Neural Network) in Figure 6 while being in 2 different categories (namely, Explanation of Deep Network Processing with Decision Trees and Explanation of Deep Network Representation with the Rol”
Ethical Decision Making during Automated Vehicle Crashes (2014, background): “Although recent research shows promise (52), rule extraction is currently in the research phase.”
Explainable Artificial Intelligence: a Systematic Review (2020, unknown): “Rule Extraction by Reverse Engineering (RxREN) [242] relies on a reverse engineering technique to trace back input neurons that cause the final result, whilst pruning the insignificant ones, and to determine the data”
Trustworthy AI: From Principles to Practices (2021, methodology): “been proposed to approximate ML models, such as random forests [317, 392] and neural networks [28, 86, 393].”
Explaining Explanations: An Approach to Evaluating Interpretability of Machine Learning (2018, methodology): “Other approaches aim to reverse engineer the neural network, notably, the RxREN algorithm, which is used in DeepRED[21].”
A Survey on the Explainability of Supervised Machine Learning (2020, methodology): “RxREN Reverse engineering Classification Pedagogical Rule-based Augasta and Kathirvalavakumar (2012) RxNCM Correctly and misclassified data ranges Classification Pedagogical Rule-based Biswas et al.”
Pruning algorithms of neural networks — a comparative study (2013, background): “Moreover a simple and comprehensible set of rules can be extracted from the network by removing the input neurons that are not mandatory for solving the problem [13, 14].”
Rule extraction from neural networks — A comparative study (2012, methodology): “The techniques of the rule extraction can be grouped into three approaches namely decompositional, pedagogical and eclectic [12].”
Deep Logic Networks: Inserting and Extracting Knowledge From Deep Belief Networks (2018, background): “Knowledge extraction after training is expected to provide explanations [10]–[14], as already mentioned.”
Questioning the AI: Informing Design Practices for Explainable AI User Experiences (2020, background): “, if-then rules [11, 29, 100] How, Why, Why not, What if”