Search Results for author:
Found 6 papers, 5 papers with code
TaCo: Targeted Concept Removal in Output Embeddings for NLP via Information Theory and Explainability
In evaluation, we show that the proposed post-hoc approach significantly reduces gender-related associations in NLP models while preserving the overall performance and functionality of the models.
Unlocking Feature Visualization for Deeper Networks with MAgnitude Constrained Optimization
However, its widespread adoption has been limited due to a reliance on tricks to generate interpretable images, and corresponding challenges in scaling it to deeper neural networks.
COCKATIEL: COntinuous Concept ranKed ATtribution with Interpretable ELements for explaining neural net classifiers on NLP tasks
COCKATIEL is a novel, post-hoc, concept-based, model-agnostic XAI technique that generates meaningful explanations from the last layer of a neural net model trained on an NLP classification task by using Non-Negative Matrix Factorization (NMF) to discover the concepts the model leverages to make predictions and by exploiting a Sensitivity Analysis to estimate accurately the importance of each of these concepts for the model.
Explainable Artificial Intelligence (XAI)
Sentiment Analysis
CRAFT: Concept Recursive Activation FacTorization for Explainability
However, recent research has exposed the limited practical value of these methods, attributed in part to their narrow focus on the most prominent regions of an image -- revealing "where" the model looks, but failing to elucidate "what" the model sees in those areas.
A survey of Identification and mitigation of Machine Learning algorithmic biases in Image Analysis
Contrarily to societal applications where a set of proxy variables can be provided by the common sense or by regulations to draw the attention on potential risks, industrial and safety-critical applications are most of the times sailing blind.
Xplique: A Deep Learning Explainability Toolbox
Today's most advanced machine-learning models are hardly scrutable.
