- Denis Coquenet, Associate professor, Université de Rennes ().
- Elisa Fromont, Professor, Université de Rennes ().
- Martial Mermillod, Professor (in Cognitive Sciences) UGA. MIA chair on "Core AI-Artificial Neural Networks" ().
- Marina Reyboz, PhD, CEA ().
- An academic CV.
- An official transcript listing classes taken and grades received.
- A short statement (maximum of 2 pages) that explains what your research interests are and why
you would like to work with us. - A copy of your most recent English report (e.g. your master report).
- Any published and relevant research papers (in English, preferably PDF format). If you have several
papers, please indicate which ones you consider the three most important ones. - A list of references (e.g., supervisors)
- Matthias De Lange, Rahaf Aljundi, Marc Masana, Sarah Parisot, Xu Jia, Ales Leonardis, Gregory
Slabaugh, Tinne Tuytelaars, "A continual learning survey: Defying forgetting in classification tasks",
IEEE Trans. Pattern Anal. Mach. Intell (TPAMI), 44:7, 2022. - Li et al., "Learning without Forgetting", European Conference on Computer Vision (ECCV) 2016
Mallya et al., "PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning",
Conference on Computer Vision and Pattern Recognition (CPPR), 2018
- Hu et al., "LoRA: Low-Rank Adaptation of Large Language Models", International Conference on
Learning Representations (ICLR), 2022 Methods in Natural language Processing (EMNLP), 2021 representations (ICLR), 2023 - A master degree in computer science, AI, or a closely related discipline.
- A strong background in computer science and mathematics.
- A scientific attitude and the ability to reason through problems.
- Excellent programming skills.
- The ability to communicate written and orally in English in a clear and precise manner.
- A pro-active and independent attitude as well as the ability to function well in a team environment.
- A good motivation for pursuing a Ph.D. and working in Rennes or Grenoble.
- Subsidized meals
- Partial reimbursement of public transport cost
-
Ingénieur Systèmes Embarqués H/F
il y a 3 semaines
FORTIL Rennes, France CDI· Poste : Pour accompagner l'équipe, vous êtes capable de prendre le lead sur tout ou partie des responsabilités métiers suivantes : · Appréhender le code développé et prendre en charge le développement de nouvelles fonctionnalités en C et C++ · Développer du firmware sur des mi ...
-
Administrateur Systèmes Et Réseaux H/F
il y a 4 jours
FORTIL Rennes, France CDI· Poste : Pour accompagner l'équipe, vous êtes capable de prendre le lead sur tout ou partie des responsabilités métiers suivantes : · Définir, mettre en place et optimiser les processus internes dans le respect des orientations stratégiques de l'entreprise · Utiliser et adminis ...
-
PhD Position at IETR
il y a 3 semaines
INSA RENNES Rennes, France À temps pleinAbout us · INSA Rennes, a founding member of the INSA Group, is the largest public engineering school in Brittany. · It welcomes 2,200 students and apprentices and graduates more than 340 engineers, 60 masters and 40 PhDs per year. · Composed of 10 teaching departments, including ...
-
PhD Position F/M Reliable Deep Neural Network Hardware Accelerators
il y a 1 semaine
INRIA Rennes, France CDDContexte et atouts du poste · Context & background: · Deep Neural Networks (DNNs) [1] are currently one of the most intensively and widely used predictive models in the field of machine learning. DNNs have proven to give very good results for many complex tasks and applications, ...
-
PhD Position F/M Trustworthy AI hardware architectures
il y a 1 semaine
INRIA Rennes, France CDDContexte et atouts du poste · Context and background: Nowadays, there is a growing and irreversible need to distribute Artificial Intelligence (AI) applications from the cloud to edge devices, where computation is largely or completely performed on distributed Internet of Thi ...
-
INRIA Rennes, France CDDPhD Position F/M Reliability Enhancement of Unconventional AI Accelerators · Le descriptif de l'offre ci-dessous est en Anglais Type de contrat : CDD · Niveau de diplôme exigé : Bac + 5 ou équivalent · Fonction : Doctorant · A propos du centre ou de la direction fonction ...
-
Cybersecurity certification engineer
il y a 5 jours
Secure IC Rennes, FrancePermanent contract (CDI), based in Rennes. · Within the Norms & Certifications Program department, Secure-IC is looking for a Cybersecurity certification engineer in permanent contract in Rennes. You will be responsible for the following tasks in particular : · Synthesis of requi ...
-
Electronic Engineer W/M
il y a 5 jours
CAILabs Rennes, FranceAre you looking to apply your electronics skills in areas such as laser shaping for space communications or industrial machining processes? Do you enjoy working in multidisciplinary teams, in a small to medium-sized company? Join Cailabs As part of the electronics department, you ...
-
PhD Position F/M Trustworthy AI hardware architectures
il y a 1 semaine
Inria Rennes, FrancePhD Position F/M Trustworthy AI hardware architectures · Level of qualifications required : Graduate degree or equivalent · Fonction : PhD Position · About the research centre or Inria department · The Inria Rennes - Bretagne Atlantique Centre is one of Inria's eight centre ...
-
PhD Position F/M Trustworthy AI hardware architectures
il y a 2 semaines
Inria Rennes, FrancePhD Position F/M Trustworthy AI hardware architectures · Graduate degree or equivalent · Fonction : PhD Position · The Inria Center is a major and recognized player in the field of digital sciences. This trend aims to address issues related to data privacy , bandwidth limitati ...
-
Stage - Cybersécurité Des Réseaux de
il y a 6 jours
SERMA Safety and Security Rennes, France**Poste et missions**: · Le stage se déroulera sur le site de Rennes (35) ou celui de Paris au sein du pôle Industrial & Embedded Cybersecurity de SERMA Safety & Security (S3). Ce service est à l'origine de la création de l'outil d'audit novateur pour le test des produits embarqu ...
-
Quality Engineer Rennes
il y a 3 semaines
Capgemini Engineering Rennes, France**Short Description**: · Notre Centre d'Expertise en software embarqué repose sur un pôle d'expertise situé à Rennes. · Notre équipe développe des composants et solutions logiciels embarqués complets dédiés à divers secteurs tels que l'industrie, l'automobile, l'aéronautique, le ...
-
Quality Engineer Rennes
il y a 3 semaines
Capgemini Engineering Rennes, France**Short Description**: · Notre Centre d'Expertise en software embarqué repose sur un pôle d'expertise situé à Rennes. · Notre équipe développe des composants et solutions logiciels embarqués complets dédiés à divers secteurs tels que l'industrie, l'automobile, l'aéronautique, le ...
-
Ingénieur Systèmes Embarqués H/F
il y a 2 semaines
FORTIL Rennes, France À temps pleinQuelles sont les missions ? · Pour accompagner l'équipe, vous êtes capable de prendre le lead sur tout ou partie des responsabilités métiers suivantes : · Appréhender le code développé et prendre en charge le développement de nouvelles fonctionnalités en C et C++ · Développer du ...
-
Administrateur(Rice) de Base de Données
il y a 3 semaines
FORTIL OUEST Rennes, FranceL'ingénieur base de données interviendra principalement dans un environnement MongoDB, MySQL, MariaDB, en sera en mesure d'intervenir au sein de l'équipe "Run" ou "Projet" de notre client. Nous prenons actuellement en main des sujets d'envergure dans les domaines de la défense, d ...
-
Administrateur Systèmes Et Réseaux H/F
il y a 2 semaines
FORTIL Rennes, France À temps pleinQuelles sont les missions ? · Pour accompagner l'équipe, vous êtes capable de prendre le lead sur tout ou partie des responsabilités métiers suivantes : · Définir, mettre en place et optimiser les processus internes dans le respect des orientations stratégiques de l'entreprise · ...
-
Administrateur(Rice) de Base de Données
il y a 2 semaines
FORTIL OUEST Rennes, FranceL'ingénieur base de données interviendra principalement dans un environnement MongoDB, MySQL, MariaDB, en sera en mesure d'intervenir au sein de l'équipe "Run" ou "Projet" de notre client. Nous prenons actuellement en main des sujets d'envergure dans les domaines de la défense, d ...
-
Applications Engineer
il y a 1 semaine
Silicon Labs Careers Rennes, France- · Meet the Team · Amazon Sidewalk is a shared network that helps devices like Amazon Echo devices, Ring Security Cams, outdoor lights, motion sensors, and Tile trackers work better at home and beyond the front door. When enabled, Sidewalk can unlock unique benefits for your dev ...
-
Security Evaluation of Ai-based Hardware
il y a 6 jours
Université de Rennes - IETR Rennes, France**Security Evaluation of AI-Based Hardware Accelerator Units**: · - Réf **ABG-120503** · - Sujet de Thèse- 20/02/2024- Sans financement dédié- Université de Rennes - IETR- Lieu de travail- Rennes - Bretagne - France- Intitulé du sujet- Security Evaluation of AI-Based Hardware Acc ...
-
Responsable Qualité Logiciel Embarqué Rennes
il y a 1 semaine
Capgemini Engineering Rennes, France**Description de l'entreprise**: · Leader mondial des services d'ingénierie et de R&D, Capgemini Engineering met en œuvre une connaissance sectorielle approfondie et la maîtrise des dernières technologies digitales et logicielles pour accompagner la convergence des mondes physiqu ...
PhD Position F/M Incremental Deep Learning for Embedded Systems - Rennes, France - INRIA
Description
Contexte et atouts du poste
Context
This PhD will occur in the context of the project Adapting ( from
the PEPR AI ( This project focuses on designing adaptive embedded
hardware architectures for AI. In this context, our team wants to design new incremental machine learning
algorithms that could serve as use cases in the Adapting project for other researchers who will focus on the
hardware architecture design.
Continual learning , also known as lifelong learning or incremental learning, is a machine learning
paradigm that focuses on the ability of a model to learn and adapt continuously over time as it encounters
new data, tasks, or concepts, without forgetting or catastrophically overwriting what it has previously learned.
In continual/incremental learning, the learned model should retain knowledge about previous tasks or data
while incorporating new information. In this PhD, we will focus on designing new resource-efficient
incremental learning algorithms that can run on embedded systems with their associated ressource and
privacy constraints. These contraints involve limited computational power, memory, and energy efficiency.
They also involve real-time processing with low latency and often deterministic behavior. Updating
embedded models is complex due to hardware limitations and the need for efficient updates while handling
data locally to enhance privacy and security.
This PhD will focus on foundation models such as well-known LLM -Large Language Models- (e.g. GPT-3.5,
Mixtral, Llama 3,...) or multimodal ones (involving for example ViT -Vision Transformer- models such as
GPT-4o, Sora, Dall-E 3) and their ability to evolve continuously in an embedded environnement.
Application process
The position is funded for 3 years (this is the standard duration of a PhD in France). The net salary is around
$2000$ euros. The PhD student will be based in Rennes ( and will make
a few stays in Grenoble during the 3-years contract.
Applications will be processed on a first-come, first-served basis until June 15, 2024.
Application Material and Procedure
Here is the supervision team:
Applicants should send these documents to the entire supervision team :
Mission confiée
Related work
Incremental learning consists in a multi-stage training in which the context (data domain, classes, or task)
evolves between each training stage. This paradigm faces the stability-plasticity dilemma. It means that the
model must continuously adapt to new contexts while avoiding catastrophic forgetting (performance on past
contexts must not deteriorate). The naive approach is the standard fine-tuning strategy in which the
parameters of the model (or part of it) are updated from one stage to another by training on the new context
only. It is known to be efficient for adaptation but it is prone to catastrophic forgetting. Several works focused
on replay strategies to tackle this challenge. It consists in managing a buffer of examples from past
contexts, which are preserved through the different training stages. Alternatives have been
proposed to avoid storing old data, for instance by learning to preserve the latent representation on the new
data through the training stage . However, current incremental foundation models do not include important
desiderata for embedded models (e.g. lack of privacy, restricted hardware resources and low energy
consumption, robustness, no need for an oracle or neurogenesis). Our current project will explore the models
[1, 2, 3,4,5,6,7] and methods having those important requirements for edge AI. Another line of research is the parameter-oriented approaches: the goal is to associate part of the model's parameters with a specific context in order to maximize the performance on both past and current contexts. This is mainly done by mapping parameters
to contexts , parameter pruning or parameter addition . Among the parameter-oriented techniques, a
recent trend focused on prompt tuning, used for transformer architectures . It consists in learning input
tokens which are prepended to the input to condition the behavior of the model whose weights are frozen.
While parameter pruning and mapping lead to saturation after many training stages, the parameter addiction
approach lead to a growing number of parameters.
A complementary approach is the knowledge-editing strategy which aims at correcting specific knowledge by locating and updating the responsible neurons.
Bibliography
Principales activités
Objectives
The objective of this PhD is to investigate incremental learning of foundation models on embedded systems.
The graduate student will initially address the question: "Are foundation models prone to catastrophic
forgetting with standard fine-tuning techniques?" by conducting comprehensive studies and experiments.
Subsequently, she/he will explore how state-of-the-art (SOTA) methods can be applied to these models,
assessing the extent to which these existing techniques provide effective solutions to the problem of
incremental learning. This phase will involve adapting and optimizing SOTA methods to suit the constraints
and requirements of embedded systems (efficiency, privacy, low energy consumption, robustness, etc.).
Finally, the PhD student will develop and propose new methodologies specifically designed to enable
foundation models to learn incrementally when deployed on embedded systems, ensuring that these models
maintain performance and adaptability over time.
What we are looking for
The ideal candidate will possess the following skills and attitudes:
Compétences
(see ideal candidate before)
Avantages
Rémunération
monthly gross salary amounting to 2100 euros
