Výsledky vyhledávání - "Pierre-Alexandre Murena"

Akademický článek

Autor: Mustafa Mert Çelikok, Pierre-Alexandre Murena, Samuel Kaski

Publikováno v: Frontiers in Artificial Intelligence, Vol 6 (2023)

Modeling has actively tried to take the human out of the loop, originally for objectivity and recently also for automation. We argue that an unnecessary side effect has been that modeling workflows and machine learning pipelines have become restricte

Externí odkaz: https://doaj.org/article/fdc4bb88f006464aa6224fc2d5c7e378

Zobrazit plný text záznamu

A Deep Learning Approach to Solving Morphological Analogies

Autor: Safa AlSaidi, Esteban Marquer, Pierre-Alexandre Murena, Miguel Couceiro, Amandine Decker

Publikováno v: Lecture Notes in Computer Science
30th International Conference on Case-Based Reasoning (ICCBR2022)
30th International Conference on Case-Based Reasoning (ICCBR2022), Sep 2022, Nancy, France. pp.159--174, ⟨10.1007/978-3-031-14923-8_11⟩
Case-Based Reasoning Research and Development ISBN: 9783031149221

International audience; Analogical proportions are statements of the form "A is to B as C is to D". They support analogical inference and provide a logical framework to address learning, transfer, and explainability concerns. This logical framework f

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::36347392b0737a93f882b0042600b1e8
https://doi.org/10.1007/978-3-031-14923-8_11

Zobrazit plný text záznamu

Measuring the Feasibility of Analogical Transfer using Complexity

Autor: Pierre-Alexandre Murena

Publikováno v: Aalto University

Publisher Copyright: © 2022 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0). Analogies are 4-ary relations of the form “A is to B as C is to D". While focus has been m

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c8a1e24cd562667e0ff945695a660651

Zobrazit plný text záznamu

A Neural Approach for Detecting Morphological Analogies

Autor: Miguel Couceiro, Amandine Decker, Pierre-Alexandre Murena, Puthineath Lay, Esteban Marquer, Safa Alsaidi

Publikováno v: IEEE DSAA 2021-The 8th IEEE International Conference on Data Science and Advanced Analytics
IEEE DSAA 2021-The 8th IEEE International Conference on Data Science and Advanced Analytics, Oct 2021, Porto / Online, Portugal. IEEE DSAA 2021
The 8th IEEE International Conference on Data Science and Advanced Analytics (DSAA)
The 8th IEEE International Conference on Data Science and Advanced Analytics (DSAA), Oct 2021, Porto/Online, Portugal
DSAA
DSAA 2021-8th IEEE International Conference on Data Science and Advanced Analytics
DSAA 2021-8th IEEE International Conference on Data Science and Advanced Analytics, Oct 2021, Porto/Online, Portugal. pp.1-10
IEEE DSAA 2021-The 8th IEEE International Conference on Data Science and Advanced Analytics, Oct 2021, Porto / Online, Portugal., IEEE DSAA 2021

Analogical proportions are statements of the form "A is to B as C is to D" that are used for several reasoning and classification tasks in artificial intelligence and natural language processing (NLP). For instance, there are analogy based approaches

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c88db8671c48e40616125ba1d313b654
https://hal.inria.fr/hal-03328841/document

Zobrazit plný text záznamu

Inferring Case-Based Reasoners’ Knowledge to Enhance Interactivity

Autor: Pierre-Alexandre Murena, Marie Al-Ghossein

Publikováno v: Case-Based Reasoning Research and Development ISBN: 9783030869564
ICCBR

When interacting with a human user, an artificial intelligence needs to have a clear model of the human’s behaviour to make the correct decisions, be it recommending items, helping the user in a task or teaching a language. In this paper, we explor

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::4af5a3ddca79de32d8b169c2d674820c
https://doi.org/10.1007/978-3-030-86957-1_12

Zobrazit plný text záznamu

On the Transferability of Neural Models of Morphological Analogies

Autor: Safa AlSaidi, Esteban Marquer, Pierre-Alexandre Murena, Puthineath Lay, Miguel Couceiro, Amandine Decker

Publikováno v: Communications in Computer and Information Science ISBN: 9783030937355

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::064d24d3ad25f0a8a3c875e62202a43c
https://doi.org/10.1007/978-3-030-93736-2_7

Zobrazit plný text záznamu

Improving Artificial Teachers by Considering How People Learn and Forget

Autor: Antti Oulasvirta, Pierre-Alexandre Murena, Carlos de la Torre-Ortiz, Aurélien Nioche

Publikováno v: IUI

The paper presents a novel model-based method for intelligent tutoring, with particular emphasis on the problem of selecting teaching interventions in interaction with humans. Whereas previous work has focused on either personalization of teaching or

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::439721bb8aa41ca9793e53c205f2e590

Zobrazit plný text záznamu

Solving analogies on words based on minimal complexity transformation

Autor: Jean-Louis Dessalles, Marie Al-Ghossein, Antoine Cornuéjols, Pierre-Alexandre Murena

Publikováno v: IJCAI
International Joint Conference on Artificial Intelligence (IJCAI-2020)
International Joint Conference on Artificial Intelligence (IJCAI-2020), Jan 2021, Kyoto, Japan. pp.1848-1854

Due to the Covid outbreak, the Conference has been postponed to January, 2021, but the proceedings have been published in 2020.; International audience; Analogies are 4-ary relations of the form “A is to Bas C is to D”. When A, B and C are fixed,

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::90aefe08ccf851eb39a6d78a9e9ecad6
https://hal.telecom-paris.fr/hal-02867163

Zobrazit plný text záznamu

Transfer Learning by Learning Projections from Target to Source

Autor: Pierre-Alexandre Murena, Antoine Cornuéjols, Raphael Olivier

Publikováno v: Lecture Notes in Computer Science ISBN: 9783030445836
IDA

Using transfer learning to help in solving a new classification task where labeled data is scarce is becoming popular. Numerous experiments with deep neural networks, where the representation learned on a source task is transferred to learn a target

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::6ccdc38801af6927f362fcd66b48a427
https://doi.org/10.1007/978-3-030-44584-3_10

Zobrazit plný text záznamu

Adaptive collaborative topic modeling for online recommendation

Autor: Marie Al-Ghossein, Pierre-Alexandre Murena, Talel Abdessalem, Antoine Cornuéjols, Anthony Barré

Publikováno v: RecSys
12. ACM Conference on Recommender Systems (RecSys)
12. ACM Conference on Recommender Systems (RecSys), Oct 2018, Vancouver, Canada. 9 p., ⟨10.1145/3240323.3240363⟩
12th ACM Conference on Recommender Systems (RecSys 2018)
12th ACM Conference on Recommender Systems (RecSys 2018), Oct 2018, Vancouver, Canada

International audience; Collaborative filtering (CF) mainly suffers from rating sparsity and from the cold-start problem. Auxiliary information like texts and images has been leveraged to alleviate these problems, resulting in hybrid recommender syst

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b7a326f1a303e621ba7ca5945dc28c92
https://doi.org/10.1145/3240323.3240363

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání