About
I’ve worn most of the well-known titles in AI/ML over twelve years — data scientist, ML engineer, AI engineer. Truth be told, I don’t know what most of these terms mean.
The deeper I go into the areas I love — mathematical statistics, representation learning, classical ML — the more I realize I know nothing. So I work through it publicly. One topic, one derivation at a time.
The power of seeing resonates with me more than the power of words. I understood transformers better through vision than through language. Images are the world.
Interests
- Geometry and topology
- Mathematical statistics and dynamical systems
- Representation learning and self-supervised vision
- Survival analysis and reliability modeling
- Machine learning, done carefully
I want to work on
- Dynamical systems and physical AI
- Space and remote sensing applications
- Perception and 3D vision
- Hyperspectral imaging and optics
On AI agents: I understand the power. I’d rather point them at the fields above than use them as an end in themselves.
Links
- GitHub: madhavpr191221
- LinkedIn: madhav-prashanth