Klas Modin PRO
Mathematician at Chalmers University of Technology and the University of Gothenburg
Mathematics of Shape Learning
PhD student project
Context
-
Artificial Neural Networks (ANN): nonlinear interpolation technique inspired by biological neural networks
-
Convolutional Neural Networks (CNN): type of ANN mainly used for image classification
- 2010–2012 CNN + GPU implementation \(\Rightarrow\) CNN Revolution!
- Quickly adopted by tech companies, today used in your computer, phone, car, ... (more to come)
Why does it work so well?
- New field: Mathematics of AI
- WASP AI/Math: initiative to make Sweden a leading country in this fast growing field
Problem addressed in project
- Today's CNN-based image classifiers identifies a cat and an elephant with very high probability
- [Geirhos, et al. 2019] Cat "painted" with elephants skin identified with very high probability as elephant
Conclusion: CNN's "see" texture where we see shape
Can we trust CNN's with human tasks?
- Approach: use Shape Analysis to construct and analyze new NN better suited for shape recognition
- Mathematics involved: Riemannian geometry, analysis, numerics, mathematical hydrodynamics, stochastic analysis
Sounds interesting?
PhD student project on shape learning
By Klas Modin
Private
PhD student project on shape learning
Presented Feb 2020 at the Information Meeting for Master Students.
