The BRAIn team (Better Representations for Artificial Intelligence) focuses on research on finding efficient representations for Artificial Intelligence (mainly Deep Learning). There are 3 main research projects and 3 main application domains:
Research Projects:
- Thrifty AI, or how to find efficient representations in the low data regime (typically few-shot or few-label learning)
- Compression of AI, or how to find efficient representations to lower the demand in computations and energy of AI systems, typically for AI on edge
- Geometry and AI, or how to leverage the geometry of latent spaces or input domains to better adapt and monitor AI systems
Application Domains:
- Computer Vision
- Neuroimagery, Cognitive Neurosciences and Biomedical Data
- Sound and other temporal signals
