Natalia is Ass. Prof. of Artificial Intelligence at the Autonomous Systems and Robotics Lab (U2IS) at ENSTA ParisTech. She also belongs to the INRIA Flowers team on developmental robotics. Her research interests include deep, reinforcement and unsupervised learning, (state) representation learning, explainable AI and AI for social good. She is working on open-ended learning and continual/lifelong learning for applications in computer vision and robotics. Her background is on knowledge engineering (semantic web, ontologies and knowledge graphs) and is interested in neural-symbolic approaches to practical applications of AI.
On diverse topics: State representation learning, Deep and Reinforcement Learning, Explainable AI, and Computer Vision for Robotics/ autonomous systems/ vehicles. Interested? Send a single pdf with CV+grades.
Intelligent Drone Swarm for Search and Rescue Operations at Sea Paper accepted at the NIPS workshop on AI for Good, 2018.
I will be co-organizing the ECML PKDD 2019 Continual Learning Workshop.
Doctoral diploma on Innovation and Entrepreneurship , 2017
European Institute of Technology (EIT Digital) (Sweden, France, Finland)
Double PhD in Artificial Intelligence, 2015
Abo Akademi University, Turku (Finland) and University of Granada (Spain)
M Sc. Soft Computing and Intelligent Systems, 2012
University of Granada (Spain)
M Sc. Computer Engineering, 2010
University of Granada (Spain)
State Representation Learning: an Overview Talk at INRIA Flowers Deep RL workshop 4/4/2018.
What I learned at the PRAIRIE PAISS Summer school, Grenoble, July 2018.
Intrinsic Motivation and Open Ended Learning (IMOL): Learnings from the 3rd IMOL (Intrinsic Motivation and Open Ended Learning) Workshop Rome 4-6 Oct 2017.
S-RL Toolbox: Reinforcement Learning (RL) and State Representation Learning (SRL) for Robotics
Continual AI is an Open Community of Researchers and Enthusiasts on Continual/Lifelong Learning and AI.
DREAM will enable robots to cope with the complexity of being an information-processing entity in domains that are open-ended both in terms of space and time. It paves the way for a new generation of robots whose existence and purpose goes far beyond the mere execution of dull tasks.