1 | Geraldin Nanfack

1

Adversarial Attacks on the Interpretation of Neuron Activation Maximization
The internal functional behavior of trained Deep Neural Networks is notoriously difficult to interpret. Activation-maximization …
Geraldin Nanfack, Alexander Fulleringer, onathan Marty, Michael Eickenberg, Eugene Belilovsky
PDF Cite
Adversarial Attacks on the Interpretation of Neuron Activation Maximization
Explaining through Transformer Input Sampling
Vision Transformers are becoming more and more the preferred solution to many computer vision problems, which has motivated the …
Alexandre Englebert, Sédrick Stassin, Geraldin Nanfack, Sidi Ahmed Mahmoudi, Valentin Delchevalerie, Xavier Siebert, Olivier Cornu, Christophe De Vleeschouwer
PDF Cite Code Project
Explaining through Transformer Input Sampling
An Experimental Investigation into the Evaluation of Explainability Methods
EXplainable Artificial Intelligence (XAI) aims at helping users to grasp the reasoning behind the predictions of an Artificial …
Sédrick Stassin, Alexandre Englebert, Gilles Peiffer, Geraldin Nanfack, Julien Albert, Nassim Versbraegen, Miriam Doh, Nicolas Riche, Benoît Frénay, Christophe De Vleeschouwer
PDF Code Project
Boundary-Based Fairness Constraints in Decision Trees and Random Forests
Decision Trees (DTs) and Random Forests (RFs) are popular models in Machine Learning (ML) thanks to their interpretability and …
Geraldin Nanfack, Valentin Delchevalerie, Benoît Frénay
PDF Cite Project
Boundary-Based Fairness Constraints in Decision Trees and Random Forests
Global Explanations with Decision Rules: a Co-learning Approach
Black-box machine learning models can be extremely accurate. Yet, in critical applications such as in healthcare or justice, if models …
Geraldin Nanfack, Paul Temple, Benoît Frénay
PDF Cite Code Project Poster Slides Video
Global Explanations with Decision Rules: a Co-learning Approach
Explaining t-SNE Embeddings Locally by Adapting LIME
Decision Trees (DTs) and Random Forests (RFs) are popular models in Machine Learning (ML) thanks to their interpretability and …
Adrien Bibal, Minh Viet Vu, Geraldin Nanfack, Benoît Frénay
PDF Cite Code Project
Explaining t-SNE Embeddings Locally by Adapting LIME
Squeeze-SegNet: a new fast deep convolutional neural network for semantic segmentation
The recent researches in Deep Convolutional Neural Network have focused their attention on improving accuracy that provide significant …
Geraldin Nanfack, Azeddine Elhassouny, Rachid Oulad Haj Thami
PDF Cite
Squeeze-SegNet: a new fast deep convolutional neural network for semantic segmentation
An example conference paper
Lorem ipsum dolor sit amet, consectetur adipiscing elit. Duis posuere tellus ac convallis placerat. Proin tincidunt magna sed ex sollicitudin condimentum.
Geraldin Nanfack, Robert Ford
Jul 1, 2013
PDF Cite Project Slides
An example conference paper