Search Results for author:
Found 21 papers, 14 papers with code
CAM-Based Methods Can See through Walls
CAM-based methods are widely-used post-hoc interpretability method that produce a saliency map to explain the decision of an image classification model.
Attention Meets Post-hoc Interpretability: A Mathematical Perspective
Attention-based architectures, in particular transformers, are at the heart of a technological revolution.
Are Ensembles Getting Better all the Time?
More precisely, in that case, the average loss of the ensemble is a decreasing function of the number of models.
Faithful and Robust Local Interpretability for Textual Predictions
Interpretability is essential for machine learning models to be trusted and deployed in critical domains.
The Risks of Recourse in Binary Classification
Algorithmic recourse provides explanations that help users overturn an unfavorable decision by a machine learning system.
Understanding Post-hoc Explainers: The Case of Anchors
In many scenarios, the interpretability of machine learning models is a highly required but difficult task.
On the Robustness of Text Vectorizers
A fundamental issue in machine learning is the robustness of the model with respect to changes in the input.
Explainability as statistical inference
The model parameters can be learned via maximum likelihood, and the method can be adapted to any predictor network architecture and any type of prediction problem.
Comparing Feature Importance and Rule Extraction for Interpretability on Text Data
Complex machine learning algorithms are used more and more often in critical tasks involving text data, leading to the development of interpretability methods.
A Sea of Words: An In-Depth Analysis of Anchors for Text Data
For text data, it proposes to explain a decision by highlighting a small set of words (an anchor) such that the model to explain has similar outputs when they are present in a document.
How to scale hyperparameters for quickshift image segmentation
Quickshift is a popular algorithm for image segmentation, used as a preprocessing step in many applications.
SMACE: A New Method for the Interpretability of Composite Decision Systems
To explain such decisions, we propose the Semi-Model-Agnostic Contextual Explainer (SMACE), a new interpretability method that combines a geometric approach for decision rules with existing interpretability methods for machine learning models to generate an intuitive feature ranking tailored to the end user.
What does LIME really see in images?
As a consequence of this analysis, we uncover a connection between LIME and integrated gradients, another explanation method.
An Analysis of LIME for Text Data
In this paper, we provide a first theoretical analysis of LIME for text data.
Looking Deeper into Tabular LIME
As an example, for linear functions we show that LIME has the desirable property to provide explanations that are proportional to the coefficients of the function to explain and to ignore coordinates that are not used by the function to explain.
Explaining the Explainer: A First Theoretical Analysis of LIME
We derive closed-form expressions for the coefficients of the interpretable model when the function to explain is linear.
When do random forests fail?
As a consequence, even highly randomized trees can lead to inconsistent forests if no subsampling is used, which implies that some of the commonly used setups for random forests can be inconsistent.
Comparison-Based Random Forests
Assume we are given a set of items from a general metric space, but we neither have access to the representation of the data nor to the distances between data points.
NEWMA: a new method for scalable model-free online change-point detection
We consider the problem of detecting abrupt changes in the distribution of a multi-dimensional time series, with limited computing power and memory.
Large sample analysis of the median heuristic
In kernel methods, the median heuristic has been widely used as a way of setting the bandwidth of RBF kernels.
Metric Learning for Temporal Sequence Alignment
The learning examples for this task are time series for which the true alignment is known.
