Neural network explanation using inversion
By Emad W. Saad, Donald C. Wunsch II. 2007
114 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
- Tameru Hailesilassie
- Thangairulappan Kathirvalavakumar
- Gethsiyal Augasta M
- Vaishak Belle
- Ioannis Papantonis
- Lale Özbakır
- Sinem Kulluk
- Adil Baykasoglu
In Computational Theory and Mathematics
- Tameru Hailesilassie
- Vaishak Belle
- Ioannis Papantonis
- Thangairulappan Kathirvalavakumar
- Gethsiyal Augasta M
- Ee-Chien Chang
- Lale Özbakır
- Sinem Kulluk
Citations in the corpus
- Rule Extraction Algorithm for Deep Neural Networks: A Review (2016, methodology): “Saad and Wunsch [24] have introduced a pedagogical approach method HYPINV, based on network inversion technique.”
- Neural Network Inversion in Adversarial Setting via Background Knowledge Alignment (2019, background): “Much research has been working on interpreting and understanding neural networks [45, 54, 63, 66, 76, 78].”
- Principles and Practice of Explainable Machine Learning (2020, methodology): “Saad and Wunsch [70] have proposed an algorithm called HYPINV, based on a network inversion technique.”
- A soft computing-based approach for integrated training and rule extraction from artificial neural networks: DIFACONN-miner (2010, background): “Saad and Wunsch II [35] proposed a new explanation algorithm which relies on network inversion.”
- Adversarial Neural Network Inversion via Auxiliary Knowledge Alignment (2019, background): “Much research has been working on interpreting and understanding neural networks [28], [65], [29], [66], [67], [68].”
- Reverse Engineering the Neural Networks for Rule Extraction in Classification Problems (2012, background): “Table 8 shows the comparison results of the proposed algorithm on three datasets namely Wisconsin breast cancer, Ionosphere and Pima Indian Diabetes with HYPINV.”
- Rule extraction from trained adaptive neural networks using artificial immune systems (2009, background): “The number of these rules and their form do not directly correspond to the number of weights or the architecture of ANN (Saad & Wunsch, 2007).”