News – Laboratoire Informatique d’Avignon

Gaelle Laperrière Ph.D. thesis defense – 09/09/2024

3 September 2024

Date: 9th of Septembre 2024 Time : 3PM Place: Ada Lovelace CERI’s amphitheater, at the Jean-Henri Fabre campus of Avignon Université. The jury will be composed of: Alexandre Allauzen, PR at Université Paris Dauphine-PSL, LAMSADE – Rapporteur Benoit Favre, PR at Aix-Marseille Université, LIS – Rapporteur Marco Dinarelli, CR at CNRS, LIG – Examiner Nathalie Camelin, MCF at Le Mans Université, LIUM – Examiner Philippe Langlais, PR at Université de Montréal, DIRO, RALI – Examiner Fabrice Lefèvre, PR at Avignon Université, LIA – Examiner Yannick Estève, PR at Avignon Université, LIA – Thesis director Sahar Ghannay, MCF at Université Paris-Saclay, LISN, CNRS – Thesis co-supervisor Bassam Jabaian, MCF at Avignon Université, LIA – Thesis co-supervisor Title: Spoken Language Understanding in a multilingual context This thesis falls within the scope of Deep Learning applied to Spoken Language Understanding. Its primary objective is to leverage existing data of large resourced annotated languages for speech semantics to develop effective understanding systems in low resourced languages. In recent years, significant advances were made in the field of automatic speech translation through new approaches that converge audio and textual modalities, the latter benefiting from vast amounts of data. By visualizing spoken language understanding as a translation task from a natural Plus d'infos

Cornet Seminar – Anna Melnykova – 10/09/2024

2 September 2024

First CORNET seminar, Tuesday 10th september 2024 11:00, room C057. Anna Melnykova from Mathematics Lab of Avignon (LMA). Abstract: Hawkes processes is a versatile probabilistic tool which permits to model a variety of real-world phenomena: earthquakes, stock markets, population dynamics. In this talk we will focus on its use in neuroscience, where they permit to model interactions between different group of neurons (or individual neurons). Furthermore, due to memory property, models based on Hawkes processes naturally embed the refractory (inter-spiking) period for each individual neuron. The focus of this talk is on numerical and statistical challenges associated with Hawkes processes (simulation, parametric and non-parametric inference, causality).

LIA Seminar – Vincent Rialle – 31/05/2024

22 May 2024

Vincent Rialle, Université de Grénoble AlpesLieu : CERI Salle 3 – C022 – 12h00 Titre : Comprendre l’IA des contraste extrêmes, médiatiques et politiques, et agir en tant que chercheur ou enseignant Résumé : L’intelligence artificielle défraie de manière croissante toutes les chroniques médiatiques depuis quelques années, avec en perspective pour 2024 quelques pires scénarios possibles mais aussi des avancées du discernement éthique, de la responsabilisation politique des états en matière de législation et régulation, et une progression des prises de conscience de l’acuité des problèmes sociaux, environnementaux et civilisationnels que pose cette technologie à l’humanité. L’exposé donnera une vue à la fois succincte et précise du paysage contrasté actuel. Puis dépassant les stratégies habituelles d’alertes par les extrêmes, qu’ils soient apocalyptiques ou enchanteurs, il présente une approche centrée sur la personne – chercheuse/chercheur dans son laboratoire, étudiant, ou toute personne intéressée par la question – et selon des ressources et principes existants et référencés (mais souvent noyés dans le flux médiatique actuel). Biographie : Vincent Rialle est maître de conférences-praticien hospitalier émérite à l’Université Grenoble Alpes (UGA, France) et enseignant bénévole à l’Université Inter-Âge du Dauphiné (UIAD) ; il est titulaire d’un doctorat en Éthique Biologique et Médicale et d’un Plus d'infos

Séminaire SLG – Tanja Schultz – 25/04/2024

22 April 2024

On Thursday 25 April at 11am, we will host a talk from Prof. Tanja Schultz on « Neural Signal Interpretation for Spoken Communication ». The room will be defined later. Please find below a short abstract and bio from Prof. Tanja Schultz. Abstract: This talk presents advancements in decoding neural signals, providing further insights into the intricacies of spoken communication. Delving into both speech production and speech perception, we discuss low latency processing of neural signals from surface EEG, stereotactic EEG, and intracranial EEG using machine learning methods. Practical implications and human-centered applications are considered, including silent speech interfaces, neuro-speech prostheses, and the detection of auditory attention and distraction in communication. This presentation aims to spark curiosity about the evolving landscape of neural signal interpretation and its impact on the future of spoken communication. Bio: Tanja Schultz received the diploma and doctoral degrees in Informatics from University of Karlsruhe and a Master degree in Mathematics and Sport Sciences from Heidelberg University, both in Germany. Since 2015 she is Professor for Cognitive Systems of the Faculty of Mathematics & Computer Science at the University of Bremen, Germany. Prior to Bremen she spent 7 years as Professor for Cognitive Systems at KIT (2007-2015) and over 20 years as Plus d'infos

Cornet Seminar – Judith Agueda Roldan Ahumada – 15/03/2024

12 March 2024

In the context of team Cornet’s seminars, Judith Agueda Roldan Ahumada (Universidad Veracruzana) will present her research work on Modeling and optimization of a vehicle routing problem in a coffee company, on March 15, 2023, at 11:35 in the meeting room. Abstract: In the central region of Veracruz, Mexico, given the weather and soil conditions, there are different companies dedicated to the coffee bean production. To carry out the different activities such as planting, harvesting,cleaning, among others, it is necessary to transport the harvesters to different agricultural lands; usually, this logistics problem is solved empirically without considering the cost per transfer. The problem, that will be shown, arose from the needing to solve a transport logistic problem for a coffee bean company in the central region of Veracruz.We consider a single vehicle with maximum capacity of N items, the vehicle starts the path with out items from a parking and it can collect the items in places that are along the way, that goes from parking to the place where the items are delivered (agricultural lands). The places are ordered consecutively, such that, once the vehicle goes through one, it can not return to the previous sites and it is Plus d'infos

SLG Seminar – Antoine Caubrière – 03/15/2024

11 March 2024

Next SLG meeting will take place on 03/15/2024, from 10 AM to 11 AM. We will host Antoine Caubrière from the company Orange, who will present his recent work Title: Representation of Multilingual Speech through Self-Supervised Learning in an Exclusively Sub-Saharan Context. Abstract: The Orange group operates in over a dozen sub-Saharan African countries with the ambition of offering services tailored to the needs of clients in this region. To provide localized and accessible services to digitally underserved and low-literate individuals, Orange is investing in the development of voice-based conversational agents to inform and assist its clients and employees.The implementation of such a service requires, first and foremost, a technological component for speech recognition and understanding.The strong linguistic diversity of the African continent, coupled with the challenges of limited annotated data, poses one of the challenges in implementing speech processing technology for these languages. One potential solution could be the utilization of self-supervised learning techniques. Leveraging this type of learning enables the training of a speech representation extractor capable of capturing rich features. This approach utilizes a large quantity of unlabeled data for pre-training a model before fine-tuning it for specific tasks. While numerous self-supervised models are shared within the Plus d'infos

LIA Doctoral Fellowship 2024

27 February 2024

The 2024 doctoral fellowship from the LIA has been awarded to the Cornet team. Several topics have been proposed, and they are available on the Adum platform. In alphabetical order by title: Interested candidates should apply on the Adum platform. Most importantly, before doing so, contact the researchers who propose the topics to discuss them further.

Position for Assistant Professor in Computer Science at Avignon Institute of Technology

27 February 2024

As part of the national synchronized recruitment campaign for teaching and research faculty in 2024, Avignon University is offering a position for an Assistant Professor in Computer Science. Teaching will take place at the Avignon University Institute of Technology, mainly in the field of Data Science, and research will be conducted at the LIA (Avignon University CS Lab). The position description is available here (in French): https://univ-avignon.fr/wp-content/uploads/2024/02/4222-IUT-MCF-27.pdf

Cornet Seminar – 23/02/2024

20 February 2024

The next seminar of the Cornet team will take place on February 23, 2024, at 11:35 a.m. in S3, and will consist of two parts. First, Sylvie Chaddad (LIA) will present her thesis topic on Stochastic Control for Optimizing Crowdfunding Project Dynamics. Then, Lorena Garrido (University of Veracruz) will present her work titled On the Monge-Kantorovich divergence. Abstract: The Monge-Kantorovich divergence is a measure of closeness between probability distributions. Historically, it arises from an optimal transport problem of sand movement, in the area of civil engineering. Today, the Monge-Kantorovich problem has given rise to many theoretical studies, as well as various applications, including data analysis. In this talk, a couple of applications in data analysis will be mentioned.

Best paper award

19 February 2024

Congratulations to Grace Tessa Masse and Abderrahim Benslimane, for the best paper award they obtained at International Conference on Computing, Networking and Communications (IEEE ICNC 2024) Title: A Secure Hierarchical Federated Learning Using Dirichlet-based Trust Management Abstract—Hierarchical Federated Learning (HFL) is a distributed machine learning training system in which a server works with several clients and edge nodes while maintaining data privacy. Distributed machine learning training systems are also known as Federated Learning, but HFL is a type of Federated Learning that utilizes a hierarchical network architecture to address computational issues when dealing with a high number of clients. However, HFL is vulnerable to attacks such as data poisoning, which may jeopardize the entire training process and result in misclassifications. As system defenders, we have to tackle this issue. Using a label-flipping attack, we investigate the effect of data poisoning attacks on HFL training. We propose a trust management-based strategy to mitigate data poisoning attacks, which assesses client trustworthiness using a Dirichlet distribution. We maintain a record of previous activities, allowing the server to enhance its knowledge based on client reliability. We demonstrate the proposed approach’s effectiveness through improvements in model performance after removing malicious clients, using the MNIST dataset Plus d'infos

1 2 3 … 8 »