The Computer Architecture and Operating System group at the Barcelona Supercomputing Center aims to carry out research on critical embedded computing systems in charge of controlling safety-related systems of cars, airplanes, trains, and satellites. Our work is mainly carried out in the context of bilateral projects with several companies (processor companies, suppliers, and OEMs in critical systems) as well as several European-funded projects. For a complete list of publications of the group in the last years, please visit: www.bsc.es/caos, https://people.ac.upc.edu/fcazorla/, https://people.ac.upc.edu/jabella/.
The present Research Engineer and PhD Student position integrates cutting-edge research with hands-on implementation, focusing on Explainable Artificial Intelligence (XAI). The role entails developing and implementing transparent AI models for decision support environments, emphasizing real-world applicability. Responsibilities span designing models for clear explanations, testing on real platforms, studying generalization mechanisms, and managing uncertainty in AI systems. The objective is to contribute substantively to XAI, bridging theory and practice for enhanced decision support in dynamic environments.
Key Duties
- Conduct a thorough study on explainability methodologies in artificial intelligence.
- Design a self-explanatory model (with a focus on neural networks) capable of providing clear and understandable explanations for decisions and internal processes.
- Undertake a theoretical study on generalization mechanisms in artificial intelligence models.
- Ensure proper management of uncertainty as a foundational step to enhance confidence and interpretation of results.
- Design specific models and strategies for communication of explainability in the context of explainable artificial intelligence.
Data de tancament: Dimecres, 31 Gener, 2024
Més posts de Recerca
Cap comentari:
Publica un comentari a l'entrada