Post-Doctorant Metacognition And Predictive Coding In Bio-Realistic Artificial Intelligence Networks H/F - INRIA

A propos d'Inria

Inria est l'institut national de recherche dédié aux sciences et technologies du numérique. Il emploie 2600 personnes. Ses 215 équipes-projets agiles, en général communes avec des partenaires académiques, impliquent plus de 3900 scientifiques pour relever les défis du numérique, souvent à l'interface d'autres disciplines. L'institut fait appel à de nombreux talents dans plus d'une quarantaine de métiers différents. 900 personnels d'appui à la recherche et à l'innovation contribuent à faire émerger et grandir des projets scientifiques ou entrepreneuriaux qui impactent le monde. Inria travaille avec de nombreuses entreprises et a accompagné la création de plus de 200 start-up. L'institut s'eorce ainsi de répondre aux enjeux de la transformation numérique de la science, de la société et de l'économie.

Post-Doctorant F/H Metacognition and Predictive Coding in Bio-Realistic Artificial Intelligence Networks

Type de contrat : CDD

Niveau de diplôme exigé : Thèse ou équivalent

Fonction : Post-Doctorant

Niveau d'expérience souhaité : Jeune diplômé

Contexte et atouts du poste
About the centre:The Inria center at the University of Bordeaux is one of the nine Inria centers in France and hasabout twenty research teams. The Inria centre is a major and recognized player in the field ofdigital sciences. It is at the heart of a rich R&D and innovation ecosystem: highly innovativeSMEs, large industrial groups, competitiveness clusters, research and higher education players,laboratories of excellence, technological research institute...Context:Every year Inria International Relations Department has a few postdoctoral positions in orderto support Inria international collaborations.The postdoctoral contract will have a duration of 24 months. The default start date isNovember 1st, 2026 and not later than January, 1st 2027. The postdoctoral fellow will berecruited by one of the Inria Centres in France but it is recommended that the time is sharedbetween France and the partner's country (please note that the postdoctoral fellow has tostart his/her contract being in France and that the visits have to respect Inria rules formissions).
Mission confiée
Candidates for postdoctoral positions are recruited after the end of their Ph.D. or after a firstpost-doctoral period: the latest eligible Ph.D. defense date will vary accordingly(approximately between November 1, 2023 and January 1, 2024).In order to encourage mobility, the postdoctoral position must take place in a scientificenvironment that is truly different from the one of the Ph.D. (and, if applicable, from theposition held since the Ph.D.); particular attention is thus paid to French or internationalcandidates who obtained their doctorate abroad.
Principales activités
Metacognition is the cognitive process by which, instead of just learning to associate aresponse or a behavior with a situation, animals (and mainly primates) monitor the functioning(and particularly errors) of simple cognitive processes, learn to inhibit automatic responsesand promote instead contextually appropriate behavioral rules.Better understanding and modeling this process is important for several reasons. In cognitiveneuroscience, it paves the way to exploring higher cognitive functions like reasoning,imagination and other kinds of deliberation-based thoughts. In Artificial Intelligence, it standson the same grounds as Generative AI and proposes different processes and algorithms thatmight remedy several weaknesses of GenAI and suggest innovative brain-inspired extensions.The Mnemosyne Inria team in Bordeaux and the Machine Learning CWI group in Amsterdamhave a long experience in cognitive computational neuroscience and have launched a project,MetaBrain, with the aim of specifying the computational mechanisms of metacognition, alsodefining relevant tasks to assess the performance of metacognitive models. In this perspective,the two teams have recently begun considering how predictive coding, a major biologicallyfounded model of cortical learning and functioning, could be used to design metacognitivefunctions (Brucklacher et al., 2025; Dora et al., 2021; Fontaine et al., 2025). Relying on theirpast experience, both teams consider applications in the visual domain.Accordingly, the role of the postdoctoral fellow to be recruited is to participate to theMetaBrain project, under the following axes:Axis 1: Specification of Metacognition and its main computational mechanisms:When several elementary competences have been learned (possibility to associate a responsewith a situation), the role of Metacognition (or cognitive control) is to control theperformances of the competences, the selection or the coordination of the most appropriateones depending on the context, or the creation of a new one. This is generally describedthrough three main mechanisms: (i) the possibility to monitor cues indicating difficulties in theprocess of problem solving (errors or conflicts between resources), in order to inhibitelementary default responses, (ii) working memory to keep in sustained activity the differentaspects to be integrated (goals and subgoals, predictions, constraints) and (iii) cognitiveflexibility corresponding to new goals and contextual rules that can be learned and integratedin the process of problem solving.Our two teams have already proposed models that address several aspects of thesemechanisms (Dagar et al., 2021; Kruijne et al., 2020; Nallapu et al., 2019; Van den Berg, 2023)and are also aware of several other models in the literature proposing other candidatemechanisms (see for example Alexander and Brown, 2015; Botvinick et al., 2001, Collins et al.,2012; Domenech et al., 2015; Miller et al, 2024; VanRullen et al., 2021). All these modelsindicate possible correspondence with cerebral circuitries and adaptive operations.Nevertheless, they are many and split these general mechanisms in different pieces which arenot always consistent and may differ under several aspects. It will be consequently importantbe become familiar with these elements, and propose a synthesis associating both a precisedescription of the mechanisms and a map of their functional dependencies.Axis 2: Integrating the framework of predictive coding:Most models of metacognition evoked above consider that the elementary competences arelearned and represented in the cortex. Generally, this is done in the models with a classicalassociative learning, whereas an alternative to this type of learning, predictive coding, isdeveloped for some years, along with strong biological and theoretical justifications (Friston,2003). This formalism has been also studied recently in our teams (Fontaine and Alexandre,2025; Brucklacher et al., 2025; Dora et al., 2021). It is particularly interesting in the perspectiveof metacognition, since it explicitly manipulates error signals and is a strong basis forgenerative models. Manipulating precision, a major parameter in predictive coding, could bean interesting way to address metacognition, generally described as a way to control hyperparametersin learning models.A major contribution of this work will be to study this formalism and propose solutions tointegrate it within a metacognitive perspective. A good way to assess such a dual model willbe to implement it within a task, as described below.Axis 3: Definition of relevant tasks in the domain of visual reasoning:Although many standard tasks have been defined and shared for simple sensorimotor control,it is not yet the case for cognitive control, generally corresponding to much more complexbehaviors. A variety of tasks have been proposed in models mentioned above but theydifferently integrate fundamental constituents such as hierarchical and temporaldependencies. In a view of standardization, the goal will be consequently to enumerateproperties that have to be assessed when developing such metacognitive models and proposeor design corresponding tasks.Subsequently, the postdoctoral fellow will work on integrating the insights from Axes 1 and 2and task definitions in this Axis, with an architecture that integrates selected mechanisms fromthe different frameworks, particularly under the perspective of extending and evaluatingmodels proposed in our teams with novel properties.This postdoc position is proposed for 24 months, starting on November 1st, 2026 and will bemainly located in the Mnemosyne team, in Bordeaux, France, with visits to the CWI partner inAmsterdam. More specifically, in addition to regular visio-meetings, a 2-3-weeks stay inAmsterdam each year will be organized.
Compétences
We are looking for a talented colleague with confirmed competences in the domain ofMachine Learning. Accordingly, programming skills related to such modeling approaches andgood knowledge about corresponding frameworks and platforms will be necessary. Pastexperience in the domain of computational neuroscience and a strong interest in cognitiveneuroscience will be very positively considered.
Avantages

- Restauration subventionnée
- Transports publics remboursés partiellement
- Congés: 7 semaines de congés annuels + 10 jours de RTT (base temps plein) + possibilité d'autorisations d'absence exceptionnelle (ex : enfants malades, déménagement)
- Possibilité de télétravail partiel et aménagement du temps de travail
- Équipements professionnels à disposition (visioconférence, prêts de matériels informatiques, etc.)
- Prestations sociales, culturelles et sportives (Association de gestion des oeuvres sociales d'Inria)
- Accès à la formation professionnelle
- Sécurité sociale

Rémunération

The grossly monthly salary will be 2788€ (before social security contribution and witholding tax)