Mouhssine founded Guardal, a defense company building resilient multi-domain sensing.
During my time at Stanford, I used RL to improve adaptive perception and foveated perception in embodied agents. My ideas included developing adaptive sensors that could dynamically switch modalities based upon prediction errors and control systems that could take input from these dynamic sensors. The unifying theme was that perception, decision making and physical action need to be designed together. I write notes on deep learning theory on my personal website.
Adaptive sensing
Sensors that switch modality depending upon what is being sensed using prediction error for a learned "forward" world model.
Foveated perception
Using real-time attention (high resolution) at those portions of a visual scene most likely to matter; this can occur when there has been a distributional shift in the data.
Embodied control
Closed-loop policies are generated and executed in real time based on information collected by the sensors.
World models
ML-trained forward models produce predictions that are compared against observed reality and serve to determine whether or not to modify sensor modalities and/or close the policy loop.
| Intelligent Systems and Networks Group | Imperial College London |
| Arbabian Lab | Stanford University |
| EMERGE Lab | New York University |
| MVA Program | ENS Paris-Saclay |
| Mathematics | Sorbonne University |