Explaining Aha! moments in artificial agents through IKE-XAI: Implicit Knowledge Extraction for eXplainable AI

Autor: Chraibi Kaadoud, Ikram, Bennetot, Adrien, Mawhin, Barbara, Charisi, Vicky, Díaz-Rodríguez, Natalia

Publikováno v: In Neural Networks November 2022 155:95-118

Explaining complex system of multivariate times series behavior

Autor: Chraibi Kaadoud, Ikram, Fahed, Lina, Tian, Tian, Haralambous, Yannis, Lenca, Philippe

Complex systems represented by multivariate time series are ubiquitous in many applications, especially in industry. Understanding a complex system, its states and their evolution over time is a challenging task. This is due to the permanent change o

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=od_______166::a2bd79d332fea3aa5fb9d118c689ad95
https://imt-atlantique.hal.science/hal-03875661

eXplainable Artificial intelligence: From machine to humans, how to make them collaborate?

Autor: Chraibi Kaadoud, Ikram

Publikováno v: WiDS 2021 : Women in data science Benguerir @ UM6P : Data science between academia and industry
WiDS 2021 : Women in data science Benguerir @ UM6P : Data science between academia and industry, MSDA (Modeling Simulation & Data Analysis), Mohammed VI Polytechnic University, Mar 2021, Ben Guerir (virtuel), Morocco

Whether it is upstream, when providing data, when implementing an architecture, or when using algorithms, humans impact AI algorithms through their cognitive biases, their habits and through the data that the algorithms learn. And in turn, the latter

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::dcc897eec118657d272a0f0c3fb5c792
https://hal.archives-ouvertes.fr/hal-03184424

Neurosmart, a story of brains and science enthusiasts

Autor: Alexandre, Frédéric, Chiron, Denis, Chraibi Kaadoud, Ikram, Courbin-Coulaud, Martine, Dagar, Snigdha, Firmo-Drumond, Thalita, Héricé, Charlotte, Hinaut, Xavier, Nallapu, Bhargav Teja, Ninassi, Benjamin, Padiolleau, Guillaume, Pagliarini, Silvia, De Quatrebarbes, Sophie, Rougier, Nicolas, Sankar, Remya, Strock, Anthony, Viéville, Thierry

Publikováno v: [Rapport Technique] RT-0509, Inria. 2020, pp.19

We propose a participatory science outreach approach allowing us to co-construct with our audiences resources aimed at understanding and demystifying the most disruptive results obtained regarding human brain by the conjunction of computer science, a

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=od_______212::29a9ea3cd2cbb2af5d7f29fc25807a1b
https://hal.inria.fr/hal-03013647/file/RT-0509.pdf

Modeling Implicit Learning : Extracting Implicit Rules from Sequences using LSTM

Autor: Chraibi Kaadoud, Ikram, Rougier, Nicolas P., Alexandre, Frédéric

Publikováno v: WiML 2019-14th Women in Machine Learning Workshop at NeurIPS 2019
WiML 2019-14th Women in Machine Learning Workshop at NeurIPS 2019, Dec 2019, Vancouver, Canada

International audience; Humans acquire different kinds of knowledge employing different types of memory systems. Implicit knowledge is a non-expressible knowledge of which the individual is not aware of and that is acquired through implicit learning.

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::b66d43ea73f52361992d80f70bc84fa2
https://hal.archives-ouvertes.fr/hal-02491042