Doctorant F/H Foundation Models of human brain function
Il y a 3 mois
Contexte et atouts du poste
One of the major directions for future neuroscience is to build on the expertise accumulated in AI-powered
cognitive systems, such as architectures that process language or visual content, but in the future will also
include motor actions, planning and navigation. While both AI and neuroscience will benefit from comparing
brain activity data with AI systems, one difficulty is that the links between AI models and brain activity
have been made in very specific contexts [1, 2, 3] and may not generalise beyond a few standard situations
(static images, language, sounds).
A recent and beneficial shift in recent years has been the development and public sharing of large-scale brain
imaging datasets, whether performed on large populations [4, 5, 6] or on small groups of individuals but with
very large amounts of data available [7, 8, 9] and – a context known as deep
phenotyping. Given the availability of such data, which are only partially or inconsistently annotated [10],
the question is: can one identify core structures of these networks that would provide relevant primitives for
fitting AI models?
Mission confiée
In this PhD, we aim to build basic models of brain function using large-scale imaging resources, from which
a network of components would be identified.
• Components refer to dictionary-like decompositions of brain data, factorising the data into sparse but
structured regions as in [11]. These topographies should be multiscale [12] and, unlike previous work,
could be provided with a precise semantic specification [13, 14, 10] inherited from the annotations
associated with the brain data.
• Network refers to a graphical model underlying the properties of these components, which would de-
scribe the interactions that exist between them. The network structure can be learned together with
the above components.
• The model should be adaptive to new individuals (personalization): given some new brain imaging data,
it should be relaxed to accommodate idiosyncrasies of the new data, based on the known properties of
the components and the features visible in the data.
While dictionary learning has already proven to be a powerful tool, the semantic, network and adaptive
features of this decomposition are novel. For the adaptive part, we will rely on a optimal transport approach
recently developed in our group, which has been shown to be the most powerful in mapping inter-individual
variability [15].
Principales activités
The work will start by collecting as many publicly available datasets as possible to enable large-scale learning.
We will then develop a multi-resolution dictionary learning strategy similar to [11] to 2k or even 4k components
(the most accurate models are currently only 1k). We will augment the learned model with contrastive
strategies that produce merging of the data, revealing statistical relationships between models. For this we
will draw inspiration fro [19, 16].
After this step, we will extend the model with the following features (these tasks can be performed in parallel
and are weakly interdependent).
• We will associate semantics with components by investigating stable predictive associations between
cognitive annotations of the data and the brain components whose signal predicts the occurrence of
these labels across datasets.
• We will learn the dependence structure of the model; this can be summarised by a classical covariance
structure, but embeddings produced by contrastive models actually contain an implicit dependence
structure that could be captured by conditional distributions of the signals in the model components.
• We will propose a scheme for adapting the model to new individual data based on the model in [15].
Unlike existing tools, this correspondence model should be able to account for all available information:
not only image domain signals, but also semantics and connectivity.
Technical developments To this end, we will revisit and extend the large-scale dictionary learning model
of [11, 12], and investigate non-linear contrastive variants of these models. We will use large-scale inference
tools to learn clean semantic associations from the data.
Validation on brain imaging analysis tasks Validation is a core step of the procedure, necessary to
validate any successive improvements to the initial model. It will consist of a selection of several core imaging
tasks that represent the expected virtues of the sought brain model: i) good representation of the existing
data, whether they come from public image databases not used to build the model, or from the existing
literature; ii) perform decoding at scale with good accuracy [10]; iii) fit of the AI model, as measured by the
amount of explained variance.
Compétences
Compétences techniques et niveau requis : Maitre de Python scientifique, neuroimagerie, apprentissage automatique.
Langues : anglais
Compétences relationnelles : -
Compétences additionnelles appréciées :-
Avantages
Subsidized meals Partial reimbursement of public transport costs Leave: 7 weeks of annual leave + 10 extra days off due to RTT (statutory reduction in working hours) + possibility of exceptional leave (sick children, moving home, etc.) Possibility of teleworking and flexible organization of working hours Professional equipment available (videoconferencing, loan of computer equipment, etc.) Social, cultural and sports events and activities Access to vocational training Social security coverage
Rémunération
Minimum remuneration: 2,100 € gross/month
Order of August 29, 2016 setting the remuneration of contract doctoral students
-
PhD Researcher in Brain Function Modeling
il y a 2 semaines
Palaiseau, Île-de-France INRIA Temps pleinJob DescriptionContext and OpportunitiesWe are seeking a highly motivated PhD researcher to join our team at INRIA and contribute to the development of novel brain function models using large-scale imaging resources. The successful candidate will have the opportunity to work on a cutting-edge project that combines neuroimaging, machine learning, and...
-
PhD Student in Brain Function Modeling
il y a 1 jour
Palaiseau, Île-de-France INRIA Temps pleinJob DescriptionWe are seeking a highly motivated and skilled PhD student to join our team at INRIA. The successful candidate will work on building basic models of brain function using large-scale imaging resources. The project aims to identify core structures of brain networks that provide relevant primitives for fitting AI models.Key ResponsibilitiesCollect...
-
PhD Researcher in Brain Function Modeling
il y a 2 semaines
Palaiseau, Île-de-France INRIA Temps pleinJob DescriptionContext and OpportunitiesWe are seeking a highly motivated PhD researcher to join our team at INRIA to work on building basic models of brain function using large-scale imaging resources. The successful candidate will have the opportunity to contribute to the development of novel methods for brain data analysis and machine learning.Research...
-
AI Neuroimaging Researcher
il y a 1 mois
Palaiseau, Île-de-France INRIA Temps pleinAbout INRIA INRIA is a leading French research institute dedicated to advancing computer science and its applications. We are renowned for our expertise in artificial intelligence, data science, and digital technologies. Job Description: AI Neuroimaging Researcher We are seeking a highly motivated and talented AI Neuroimaging Researcher to join our team....
-
PhD Researcher in Brain Function Modeling
il y a 1 semaine
Palaiseau, Île-de-France INRIA Temps pleinJob DescriptionContext and OpportunitiesWe are seeking a highly motivated PhD researcher to join our team at INRIA to work on building basic models of brain function using large-scale imaging resources. The successful candidate will contribute to the development of novel methods for brain data analysis and machine learning, with a focus on identifying core...
-
PhD Researcher in Brain Function Modeling
il y a 3 semaines
Palaiseau, Île-de-France INRIA Temps pleinJob Description**Mission and Objectives**We are seeking a highly motivated PhD researcher to join our team at INRIA to work on a project focused on building basic models of brain function using large-scale imaging resources. The successful candidate will be responsible for identifying a network of components that can provide relevant primitives for fitting...
-
PhD Researcher in Brain Function Modeling
il y a 6 jours
Palaiseau, Île-de-France INRIA Temps pleinJob DescriptionContext and OpportunitiesWe are seeking a highly motivated PhD researcher to join our team at INRIA, working on building basic models of brain function using large-scale imaging resources. The successful candidate will contribute to the development of novel methods for brain data analysis, leveraging recent advances in AI-powered cognitive...
-
PhD Researcher in Brain Function Modeling
il y a 4 jours
Palaiseau, Île-de-France INRIA Temps pleinJob DescriptionContext and OpportunitiesWe are seeking a highly motivated PhD researcher to join our team at INRIA, working on building basic models of brain function using large-scale imaging resources. The successful candidate will contribute to the development of novel methods for brain data analysis, leveraging recent advances in AI-powered cognitive...
-
Label Efficient 3D Detection with Foundation Models
il y a 1 semaine
Palaiseau, France CEA Temps pleinDescription du poste **Domaine**: - Mathématiques, information scientifique, logiciel **Contrat**: - Stage **Intitulé de l'offre**: - Label Efficient 3D Detection with Foundation Models H/F **Sujet de stage**: - In this internship, you will contribute to breakthrough research in areas critical to autonomous driving, robotics, and augmented reality....
-
Palaiseau, France Inria Temps pleinA propos du centre ou de la direction fonctionnelleLe centre de recherche Inria de Saclay a été créé en 2008. Sa dynamique s'inscrit dans le développement du plateau de Saclay, en partenariat étroit d'une part avec le pôle de l'Université Paris-Saclay et d'autre part avec le pôle de l'Institut Polytechnique de Paris . Afin de construire une...
-
Label Efficient 3D Detection With Foundation Models H/F
il y a 7 jours
Palaiseau, France CEA Temps plein3D object detection is a critical component of many applications such as autonomous driving, robotics, and augmented reality, where having a precise understanding of the 3D environment is crucial. In the context of 3D object detection, a key challenge lies in the high cost of annotating 3D bounding boxes, making IT difficult to scale supervised learning...
-
Post-doctorant ou Post-doctorante en Modèle
Il y a 4 mois
Palaiseau, France Télécom SudParis Temps pleinPoursuivre nos travaux de recherche sur la définition d’un modèle d’attaque des CPS (Les systèmes cyber-physiques) qui soit indépendant du langage et basé sur les ontologies, combinant les graphes typés et attribués avec les graphes de connaissance pour l’explicabilité. - Implémenter un prototype de ce modèle utilisant le langage de...
-
Post-doctorant (F/H) Sructured Riemannian
il y a 3 semaines
Palaiseau, France Inria Temps plein**Type de contrat **:CDD **Niveau de diplôme exigé **:Thèse ou équivalent **Fonction **:Post-Doctorant **A propos du centre ou de la direction fonctionnelle**: - Le centre de recherche Inria de Saclay a été créé en 2008. Sa dynamique s’inscrit dans le développement du plateau de Saclay, en partenariat étroit d’une part avec le pôle de...
-
Post-doctorant en Physique des Plasmas
il y a 4 semaines
Palaiseau, Île-de-France CNRS Temps pleinInformations Générales Titre de l'Offre : Post-doctorant en Physique des Plasmas (H/F) Compétences Souhaitées Nous recherchons un post-doctorant pour rejoindre notre équipe de recherche et développement dans le domaine de la physique des plasmas. Le candidat idéal sera un physicien des plasmas expérimenté avec une solide formation en physique...
-
Doctorant(E) (H/F) Pour La Caractérisation Des
il y a 4 semaines
Palaiseau, France CNRS Temps pleinCette offre est disponible dans les langues suivantes: - Français - Anglais Date Limite Candidature : lundi 30 septembre 2024 23:59:00 heure de Paris **Informations générales**: **Intitulé de l'offre **:Doctorant(e) H/F pour la caractérisation des structures de l’atmosphère solaire pour la mission SolO** Référence : UMR7644-TAHAMA-002 Nombre de...
-
Palaiseau, Essonne, France Inria Temps pleinA propos du centre ou de la direction fonctionnelleLe centre de recherche Inria de Saclay a été créé en 2008. Sa dynamique s'inscrit dans le développement du plateau de Saclay, en partenariat étroit d'une part avec le pôle de l'Université Paris-Saclay et d'autre part avec le pôle de l'Institut Polytechnique de Paris. Afin de...
-
Palaiseau, France Inria Temps pleinA propos du centre ou de la direction fonctionnelleLe centre de recherche Inria de Saclay a été créé en 2008. Sa dynamique s'inscrit dans le développement du plateau de Saclay, en partenariat étroit d'une part avec le pôle de l'Université Paris-Saclay et d'autre part avec le pôle de l'Institut Polytechnique de Paris. Afin de...
-
Doctorant Ccd
il y a 4 jours
Palaiseau, France CNRS Temps pleinCette offre est disponible dans les langues suivantes: - Français - Anglais Date Limite Candidature : lundi 21 octobre 2024 23:59:00 heure de Paris **Informations générales**: **Intitulé de l'offre **:Doctorant CCD (H/F) : Photovoltaïques à couche mince émergentes dans un espace agricole : stabilité et interaction avec...
-
Palaiseau, Île-de-France Inria Temps pleinAbout the Research CenterThe Inria Saclay research center was established in 2008 and plays a vital role in the development of the Saclay plateau, closely collaborating with the University of Paris-Saclay and the Institut Polytechnique de Paris. In 2021, strategic agreements were signed with these key partners to foster an ambitious site policy.The center...
-
Doctorant Nanospintronique Graphene
il y a 1 mois
Palaiseau, France CNRS Temps pleinCette offre est disponible dans les langues suivantes: - Français - Anglais Date Limite Candidature : vendredi 20 septembre 2024 23:59:00 heure de Paris **Informations générales**: **Intitulé de l'offre **:Doctorant nanospintronique graphene (H/F)** Référence : UMR137-BRUDLU-001 Nombre de Postes : 1 Lieu de travail : PALAISEAU Date de publication :...
