Marouane Il Idrissi- PhD
- Postdoctoral Researcher at University of Quebec in Montreal
Marouane Il Idrissi
- PhD
- Postdoctoral Researcher at University of Quebec in Montreal
Postdoctoral Fellow @ UQÀM
About
12
Publications
927
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
55
Citations
Introduction
I am interested in all aspects of machine learning interpretability, especially of non-linear models with dependent inputs
Skills and Expertise
Current institution
Publications
Publications (12)
Cooperative game theory methods, notably Shapley values, have significantly enhanced machine learning (ML) interpretability. However, existing explainable AI (XAI) frameworks mainly attribute average model predictions, overlooking predictive uncertainty. This work addresses that gap by proposing a novel, model-agnostic uncertainty attribution (UA)...
Machine learning algorithms, which have significantly contributed to modern artificial intelligence (AI) advancement, have repeatedly demonstrated their performance in predicting complex tasks. However, despite the potential benefits of using these methods for modeling critical industrial systems (computation time, data value, hybridization between...
One of the main challenges for interpreting black-box models is the ability to uniquely decompose square-integrable functions of non-mutually independent random inputs into a sum of functions of every possible subset of variables. However, dealing with dependencies among inputs can be complicated. We propose a novel framework to study this problem,...
Concerns have been raised about possible cancer risks after exposure to computed tomography (CT) scans in childhood. The health effects of ionizing radiation are then estimated from the absorbed dose to the organs of interest which is calculated, for each CT scan, from dosimetric numerical models, like the one proposed in the NCICT software. Given...
Understanding the behavior of a black-box model with probabilistic inputs can be based on the decomposition of a parameter of interest (e.g., its variance) into contributions attributed to each coalition of inputs (i.e., subsets of inputs). In this paper, we produce conditions for obtaining unambiguous and interpretable decompositions of very gener...
Performing (variance-based) global sensitivity analysis (GSA) with dependent inputs has recently benefited from cooperative game theory concepts.By using this theory, despite the potential correlation between the inputs, meaningful sensitivity indices can be defined via allocation shares of the model output's variance to each input. The ``Shapley e...
Robustness studies of black-box models is recognized as a necessary task for numerical models based on structural equations and predictive models learned from data. These studies must assess the model's robustness to possible misspecification of regarding its inputs (e.g., covariate shift). The study of black-box models, through the prism of uncert...
Reliability-oriented sensitivity analysis methods have been developed for understanding the influence of model inputs relative to events which characterize the failure of a system (e.g., a threshold exceedance of the model output). In this field, the target sensitivity analysis focuses primarily on capturing the influence of the inputs on the occur...
![Figure 1: Inspired from [41]. Illustration scheme of the effect of two...](profile/Marouane-Il-Idrissi/publication/348647876/figure/fig1/AS:982291379658755@1611207923222/nspired-from-41-Illustration-scheme-of-the-effect-of-two-inputs-X-1-and-X-2-on-an_Q320.jpg)
Reliability-oriented sensitivity analysis methods have been developed for understanding the influence of model inputs relatively to events characterizing the failure of a system (e.g., a threshold exceedance of the model output). In this field, the target sensitivity analysis focuses primarily on capturing the influence of the inputs on the occurre...
