Rule extraction from trained adaptive neural networks using artificial immune systems
By Humar Kahramanli, Novruz M. Allahverdi. 2009
79 citations recorded by the source corpus.
Subfields: Artificial Intelligence, Biomedical Engineering
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
- Tameru Hailesilassie
- Vaishak Belle
- Ioannis Papantonis
- Thangairulappan Kathirvalavakumar
- Gethsiyal Augasta M
- Shifei Ding
- Lale Özbakır
- Ru Nie
In Biomedical Engineering
- Lale Özbakır
- Thangairulappan Kathirvalavakumar
- Sinem Kulluk
- Adil Baykasoglu
- Tameru Hailesilassie
- Gethsiyal Augasta M
Citations in the corpus
- Rule Extraction Algorithm for Deep Neural Networks: A Review (2016, methodology): “An eclectic approach algorithm that uses artificial immune system (AIS) is proposed by Kahramanli and Allahverdi [32].”
- Principles and Practice of Explainable Machine Learning (2020, background): “An analogous eclectic approach can be found in [42], where the goal is to generate rules from a NN, using so-called artificial immune system (AIS) [22] algorithms.”
- A soft computing-based approach for integrated training and rule extraction from artificial neural networks: DIFACONN-miner (2010, methodology): “59 24 Kahramanlı and Allahverdi [23]”
- Global Research on Artificial Intelligence from 1990-2014: Spatially-Explicit Bibliometric Analysis (2016, methodology): “The latest research in AI methods is the artificial endocrine system (AES), which is introduced into the field of AI [6,67–69].”
- Reverse Engineering the Neural Networks for Rule Extraction in Classification Problems (2012, methodology): “Kahramanli and Allahverdi [43] have proposed a method to extract rules from trained adaptive neural networks using artificial immune systems.”
- Rule extraction from neural networks — A comparative study (2012, methodology): “The problem posed here is to predict whether a patient would test positive or negative for diabetes according to the criteria given by World Health Organization (WHO).”
- Extreme learning machine: algorithm, theory and applications (2013, methodology): “A sign-bi-power activation function is proposed by Li et al. (2012) to accelerate Zhang neural network to finite-time convergence.”