1 code implementation • 31 May 2023 • Saud Hakem Al Harbi, Lionel Nganyewou Tidjon, Foutse khomh
In this paper, we propose a comprehensive framework incorporating RDPs into ML pipelines to mitigate risks and ensure the ethical development of AI systems.
no code implementations • 28 Nov 2022 • Mohamed Raed El aoun, Lionel Nganyewou Tidjon, Ben Rombaut, Foutse khomh, Ahmed E. Hassan
In this paper, we present a qualitative and quantitative analysis of the most frequent dl libraries combination, the distribution of dl library dependencies across the ml workflow, and formulate a set of recommendations to (i) hardware builders for more optimized accelerators and (ii) library builder for more refined future releases.
1 code implementation • 3 Nov 2022 • Lionel Nganyewou Tidjon, Foutse khomh
Next, we compare the different TDA techniques (i. e., persistence homology, tomato, TDA Mapper) and existing techniques (i. e., PCA, UMAP, t-SNE) using different classifiers including random forest, decision tree, xgboost, and lightgbm.
1 code implementation • 30 Jun 2022 • Lionel Nganyewou Tidjon, Foutse khomh
Attacks from the AI Incident Database and the literature are used to identify vulnerabilities and new types of threats that were not documented in ATLAS.
1 code implementation • 23 Jun 2022 • Lionel Nganyewou Tidjon, Foutse khomh
In this paper, we examine trust in the context of AI-based systems to understand what it means for an AI system to be trustworthy and identify actions that need to be undertaken to ensure that AI systems are trustworthy.
no code implementations • 12 May 2022 • Lionel Nganyewou Tidjon, Foutse khomh
Next, we analyze the current level of AI readiness and current implementations of ethical AI principles in different countries, to identify gaps in the implementation of AI principles and their causes.