Post-Doctoral Research Visit F/M Modelling Action-Perception Mechanisms with Hierarchical Reservoirs

Inria, the French national research institute for the digital sciences; France; Sur place; EUR 35 000 - 50 000; Plein temps

Résumé du poste

A French national research institute is recruiting a Researcher for a post-doctoral project focused on developing a dynamic neuronal model of vocal processing. The role involves creating models based on recurrent neural networks, exploring connections between human and bird song learning, and supervising interns. A PhD in a related field and strong programming skills are required. Competitive benefits and flexible working hours are offered.

Prestations

Subsidised meals

Partial reimbursement of transport costs

7 weeks of annual leave

Possibility of teleworking

Professional equipment available

Social and sporting activities

Qualifications

• Strong background in machine learning or data mining preferred.
• Experience with scientific libraries like Numpy/Scipy.
• Good knowledge of mathematics essential.

Responsabilités

• Developing reservoir models and integrating into ReservoirPy.
• Supervising interns related to the project.
• Collaborating to find correlates between models and recordings.

Connaissances

Python programming

Mathematics

Machine learning

Data mining

Neuroscience interest

Formation

PhD in Computer Science or related field

Description du poste

Inria, the French national research institute for the digital sciences

Organisation/Company Inria, the French national research institute for the digital sciences Research Field Computer science Researcher Profile Recognised Researcher (R2) Country France Application Deadline 15 Dec 2025 - 00:00 (UTC) Type of Contract Temporary Job Status Full-time Hours Per Week 38.5 Offer Starting Date 1 Jan 2026 Is the job funded through the EU Research Framework Programme? Not funded by a EU programme Reference Number 2025-09543 Is the Job related to staff position within a Research Infrastructure? No

Offer Description

When we listen to a song, or listening at the radio, our brain needs to parse incoming stimuli incrementally and on the fly. When we learn a song, we learn to imitate what we hear by trial and error, we try to reproduce the sounds we hear. There is converging evidence that (song, language or gesture) production and perception are not separated processes in the brain, they are rather interwoven. This interweaving is for instance what enables people to predict themselves and each other [6]. Interweaving of action and perception is important because it allows a learning agent (e.g. a baby, a bird or a model) to learn from its own actions: for instance, by learning the perceptual consequences (e.g. the heard sounds) of its own actions (e.g. vocal productions) during babbling. Thus, the agent will learn in a self‑supervised way. This kind of learning is more biologically plausible than supervised learning which assumes the availability of “teacher signals” which have to be designed by the modeller. Self‑supervised learning is fundamental for developmental processes such as babbling. Schwartz et al. [11] propose that perception and action are co‑structured in the course of speech development: gestures are perceptually‑shaped, they form a perceptuo‑motor unit. A clear neuronal model explaining which are the mechanisms shaping such perceptuo‑motor units through development is missing.

This post‑doctoral project will be conducted over a 13‑month period, potentially renewable, to allow for in‑depth investigation of developmental sequence learning mechanisms.

The general aim of the ANR DeepPool project is to build a dynamic neuronal model of vocal processing and production: the model should be developmental, hierarchical and use action‑perception mechanisms. This multi‑scale model will span from sensorimotor vocal imitation towards processing and production of long sequences. It will use incremental learning schemes, with goal‑directed exploration and seek symbol emergence. We want to create a generic action‑perception mechanism that (i) would enable action and perception to shape one another, (ii) while allowing to bootstrap the development of representations from raw sound perceptions, and (iii) which could be stacked as layers of a hierarchical architecture. More info on the ANR DeepPool project: https://team.inria.fr/mnemosyne/deeppool/

The post‑doc project will explore one or several of the topics of the ANR project above. The methods developed will be based on Recurrent Neural Network (RNN), reservoir in particular, but could also use emerging hybrid models in-between Transformers and reservoirs [14] that we create in the team. A reservoir [3] is a random recurrent neural network made of non‑linear units that have been used to model various cortical areas [2, 12]. Reservoirs do not involve unfolding of time like BPTT used in LSTMs. In order to build action‑perception mechanisms we will embed various concepts from incremental, developmental, reinforcement and unsupervised learning. In particular, we will build on top of preliminary results we have on distal learning with reservoirs [4]. We will also use and develop new reinforcement learning rules adapted to reservoir computing, such as Hebbian exploratory rules [7], that we will combine with unsupervised learning rules that we previously developed such as Dynamic Self‑Organizing Maps (DSOM) [9]. Moreover, we will enhance such models with a robust long‑term memory mechanism that we recently developed [12].

We will start by implementing the full sensorimotor architecture that we defined in our review [8]. We will build on our recent results both on human speech and birdsong data. For instance, on the songbird side, we built a simple sensorimotor model using a reservoir as the perceptive decoder, a simple Hebbian learning rule for the inverse model, and a Generative Adversarial Network (GAN) as the sound generator given the motor commands. This model is able to reproduce faithfully canary syllables using only 3‑dimensional latent space [13, 14]. In order to create the core action‑perception layer, the first steps will be to incorporate a forward model and replace the GAN by a reservoir. Later on, we will stack several of these layers at different levels of hierarchy in order to extract chunks (i.e. groups of acoustic elements) of increasing size and complexity. The models will be bootstrapped from goal‑directed learning (e.g. vocal imitation). Model features will not to be predefined by the modeller but they will emerge through developmental processes. Because we will be using similar model components, we will be able to apply similar analysis methods, thus facilitating multi‑scale analyses.

The RNN mechanisms developed will be applied on human speech and bird songs, because both share similar properties adequate for the project: humans and birds learn to imitate the complex sounds that their fellows produce; they developmentally learn them starting from a babbling exploration phase; both bird songs and human language share a hierarchical organisation of elements with increasing chunk sizes; temporal context is key to make decisions on chunks (i.e. delimitation of chunk boundaries is ambiguous if the context is ignored); and vocal production models are available for both human and bird (e.g. VocalTractLab for human voice) [8].

Generic models, such as random reservoirs, can have a cross‑domain impact, opening potential adaptations to non‑vocal tasks. The methods and neural mechanisms that will be developed will not be limited to audio applications, but will be generic enough to be also applied to other domains such as motor gesture learning. Because such methods will be based on online, incremental and loosely supervised learning, they could provide more efficient methods useful for machine learning and artificial intelligence domains. Moreover, such sensorimotor models will be use as tools to analyse neuroscience experimental data of our collaborators with a new perspective, and could help in the long run to better understand mechanisms at work in speech rehabilitation therapies.

[1] M. H. Christiansen, N. Chater, P. W. Culicover. Creating language: Integrating evolution, acquisition, and processing. MIT Press, 2016.
[2] Hinaut, P.F. Dominey. Real‑Time Parallel Processing of Grammatical Structure in the Fronto‑Striatal System: A Recurrent Network Simulation Study Using Reservoir Computing. PloS ONE 8(2): e52946. 2013. doi:10.1371/journal.pone.0052946
[3] H. Jaeger, H. Haas (2004). Harnessing nonlinearity: Predicting chaotic systems and saving energy in wireless communication. science, 304(5667), 78–80.
[4] Juven, X. Hinaut. Cross‑Situational Learning with Reservoir Computing for Language Acquisition Modelling. International Joint Conference on Neural Networks, Glasgow, UK. July 2020.
[5] F. Pulvermüller, L. Fadiga. Active perception: sensorimotor circuits as a cortical basis for language. Nature Reviews Neuroscience, 11(5):351–360, Apr. 2010.
[6] M. Pickering, S. Garrod. An integrated theory of language production and comprehension. Behavioral and brain sciences, 36(4):329–347, 2013.
[7] A. Pitti et al. Gated spiking neural network using iterative free‑energy optimization and rank‑order coding for structure learning in memory sequences. Neural Networks, 121:242–258, Jan. 2020.
[8] Pagliarini, A. Leblois, and X. Hinaut. Vocal imitation in sensorimotor learning models: a comparative review. IEEE Journal of Transaction in Cognitive Develomental Systems. 2020.
[9] Rougier, & Y. Boniface. (2011) Dynamic self‑organising map. Neurocomputing, 74(11), 1840‑1847.
[10] Rougier (2019) Pourquoi votre chat est nul aux échecs et pourtant plus intelligent qu’une IA. The Conversation. ⟨hal-02322085⟩ https://theconversation.com/pourquoi-votre-chat-est-nul-aux-echecs-et-p…
[11] J.-L. Schwartz, A. Basirat, L. Ménard, and M. Sato. The perception‑for‑action‑control theory (PACT): A perceptuomotor theory of speech perception. J. of Neuroling., 25(5):336–354, Sept. 2012.
[12] Strock, X. Hinaut, N. Rougier (2020) A Robust Model of Gated Working Memory. Neural Computation, Massachusetts Institute of Technology Press (MIT Press), pp.1‑29.
[13] Pagliarini, A. Leblois, and X. Hinaut (2021) Canary Sensorimotor Model with RNN‑Decoder and Low‑dimensional GAN Generator. ICDL
[14] Y. Bendi‑Ouis, X. Hinaut (preprint 2025) Echo State Transformer: Attention Over Finite Memories. 2025. Preprint, hal‑05080235v2. https://hal.science/hal-05080235/

• Developping reservoir models based on ReservoirPy and integrate them in the ReservoirPy github as tools for the community
• Use computer clusters (Plafrim, Jean Zay, …) to evaluate big version of the model to test how their scale to numerous and/or high‑dimensional data
• Supervise interns related to the project
• Collaborate with colleagues to find correlates between models developed and birds/human recordings (e.g. fMRI, electrophysiology recordings)
• Communicate on the results in conferences and journals
• Contribute to current team projects and collaborations with his/her expertise
• Good background in maths and computer science;
• A strong interest for neuroscience and the cognitive processes underlying learning;
• Python programming with experience in scientific libraries Numpy/Scipy (or similar programming language: matlab, etc.);
• Experience in machine learning or data mining is preferred;
• Independence and ability to manage a project;

Languages: FRENCH (Level Basic)

Languages: ENGLISH (Level Good)

Additional Information

• Subsidised meals
• Partial reimbursement of public transport costs
• Leave: 7 weeks of annual leave + 10 days of RTT (full‑time basis) + possibility of special leave (e.g. sick children, moving house)
• Possibility of partial teleworking and flexible working hours
• Professional equipment available (videoconferencing, loan of IT equipment, etc.)
• Social, cultural and sporting activities (Inria Social Welfare Association)

Selection process

Thank you to send:
- A detailed CV with a description of the PhD and a complete list of publications with the two most significant ones highlighted.
- A motivation letter with a description of the candidate interests and planned methodology to tackle the research project.
- Support letters (mandatory)