[ANR-JCJC MIMICO] 3 years post-doctoral position on machine learning surrogate models for the e[]

[ANR-JCJC MIMICO] 3 years post-doctoral position on machine learning surrogate models for the exploration and calibration of agent-based simulations

The University of Toulouse Capitole is recruiting a post-doctoral fellow for its IRIT laboratory (Institut de Recherche en Informatique de Toulouse) as part of the ANR-JCJC MIMICO (http://www.irit.fr/MIMICO). The post-doctoral fellow will join the SMAC (Cooperative Multi-Agent System) team.

PRESENTATION OF THE ANR-JCJC MIMICO PROJECT

Agent-based models (ABMs) are interesting tools for modelling and studying complex phenomena in which many heterogeneous entities with nonlinear interactions are geographically distributed and modelled at different scales. The MIMICO project proposes to design and evaluate a new approach based on the construction of a surrogate model to emulate the relationship between a scenario and the results of the agent model. The key assumption is that if the learning algorithm is allowed to choose the data it learns from, it will perform better with less training. The framework is evaluated on two fields of application: the evaluation of the impact of new urban policies on the mobility model, and the calibration of the dense crowd simulation.

MAIN ACTIVITIES

As part of the SMAC team, you will carry out your research on the themes of ensemble machine learning and active learning for the exploration and calibration of multi-agent models.

CANDIDATE PROFILE

1. PhD in Computer Science or Mathematics
2. Experience in machine learning (ensemble learning, active learning, surrogate models) demonstrated by recent publications
3. Knowledge of agent modelling and model calibration issues is appreciable
4. Ability to work in a team and supervise PhD students, research engineers and interns

#J-18808-Ljbffr

Location: France, FR

Posted Date: 11/23/2024