Rule extraction from neural networks via decision tree induction

By Makoto Sato, Hiroshi Tsukimoto. 2001

133 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computational Theory and Mathematics, Information Systems, 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 Artificial Intelligence

1. Francisco Herrera
2. Salvador Garcia
3. Daniel Molina
4. Vaishak Belle
5. Ioannis Papantonis
6. Leilani H. Gilpin
7. Ben Z. Yuan
8. Michael A. Specter

In Computational Theory and Mathematics

1. Francisco Herrera
2. Salvador Garcia
3. Daniel Molina
4. Sergio Gil-Lopez
5. Ben Z. Yuan
6. David Bau
7. Michael A. Specter
8. Vaishak Belle

In Information Systems

1. Salvador Garcia
2. Francisco Herrera
3. Ben Z. Yuan
4. David Bau
5. Michael A. Specter
6. Vaishak Belle
7. Leilani H. Gilpin
8. Lalana Kagal

In Program Analysis & Verification

1. Ben Z. Yuan
2. David Bau
3. Michael A. Specter
4. Vaishak Belle
5. Leilani H. Gilpin
6. Lalana Kagal
7. Eneldo Loza Mencía
8. Frederik Janssen

Citations in the corpus

• Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI (2019, positive): “One of these few works is DeepRED algorithm [257] , which extends the de-compositional approach to rule extraction (splitting at neuron level) presented in [259] for multi-layer neural network by adding more decision trees and rules.”
• Explaining Explanations: An Overview of Interpretability of Machine Learning (2018, methodology): “One such method is DeepRED [21], which demonstrates a way of extending the CRED [22] algorithm (designed for shallow networks) to arbitrarily many hidden layers.”
• Rule Extraction Algorithm for Deep Neural Networks: A Review (2016, methodology): “An algorithm called CRED [17] extract both continuous and discrete rules by using decision tree from pre-trained ANN.”
• Principles and Practice of Explainable Machine Learning (2020, methodology): “neuron-level rather than the whole model are called decompositional. [63] propose a method for producing if-else rules from NNs, where model training and rule generation happen at the same time. CRED [71] is a dierent approach that utilizes decision trees in order to represent the extracted rules. K”
• DeepRED - Rule Extraction from Deep Neural Networks (2016, methodology): “5 based on the neural network’s inputs (adapted from [12]).”
• Explaining Explanations: An Approach to Evaluating Interpretability of Machine Learning (2018, methodology): “One such method is DeepRED [21], which demonstrates a way of extending the CRED [22] algorithm (designed for shallow networks) to arbitrarily many hidden layers.”