Orthogonal search-based rule extraction (OSRE) for trained neural networks: a practical and efficient approach
By Terence Anthony Etchells, Paulo J. G. Lisboa. 2006
112 citations recorded by the source corpus.
Subfields: Artificial Intelligence, Computational Theory and Mathematics
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
- Marco F. Huber
- Nadia Burkart
- Thangairulappan Kathirvalavakumar
- Gethsiyal Augasta M
- Mohammed Berrada
- Amina Adadi
- Gesina Schwalbe
- Bettina Finzel
In Computational Theory and Mathematics
- Nadia Burkart
- Marco F. Huber
- Thangairulappan Kathirvalavakumar
- Gethsiyal Augasta M
- Mohammed Berrada
- Amina Adadi
- Tameru Hailesilassie
- Vaishak Belle
Citations in the corpus
- Peeking Inside the Black-Box: A Survey on Explainable Artificial Intelligence (XAI) (2018, background): “the view of the underlying ANN is opaque, the Orthogonal Search-based Rule Extraction algorithm (OSRE) from [119] is a successful pedagogical methodology often applied in biomedicine.”
- Reverse Engineering the Neural Networks for Rule Extraction in Classification Problems (2012, methodology): “Most of these algorithms such as NeuroRule [26], RX [27], GLARE [28] and OSRE [29] works well on data with only discrete attributes.”
- A Survey on the Explainability of Supervised Machine Learning (2020, methodology): “OSRE Orthogonal search-based Classification Pedagogical Rule-based Etchells and Lisboa (2006)”
- Rule extraction from neural networks — A comparative study (2012, methodology): “Most of these algorithms such as NeuroRule [6], RX [7], GLARE [8] and OSRE [9] work well on data with discrete attributes only.”
- Deep Logic Networks: Inserting and Extracting Knowledge From Deep Belief Networks (2018, unknown): “Knowledge extraction after training is expected to provide explanations [10]–[14], as already mentioned.”