Block Seminar: The Role of Geometry in Machine Learning Techniques

Time: Tuesdays 12:15 – 13:45 (First Meeting: 20 April 2021)

Location: Microsoft Teams

Lecturer: Dr. Fech Scen Khoo

Suitable for: BSc Computational Linguistics, MSc Language Science and Technology, and related disciplines

Registration: Please send an email to (by 13 April)


  • A tutorial on Fisher information, A. Ly, M. Marsman, J. Verhagen, R. Grasman and E-J. Wagenmakers
  • Information geometry on hierarchy of probability distributions, S-i. Amari
  • Fisher information distance: a geometrical reading, S. I. R. Costa, S. A. Santos and J. E. Strapasson
  • Hyperbolic geometry, Charles Walkden, Lecture notes
  • Universal statistics of Fisher information in deep neural networks: mean field approach, R. Karakida, S. Akaho and S-i. Amari
  • A survey of optimization methods from a machine learning perspective, S. Sun, Z. Cao, H. Zhu and J. Zhao
  • Optimization methods on Riemannian manifolds and their application to shape space, W. Ring and B. Wirth

Papers for discussions:

  • Poincaré Glove: hyperbolic word embeddings, A. Tifrea, G. Bécigneul and O-E. Ganea
  • Geometric deep learning: going beyond Euclidean data, M. M. Bronstein, J. Bruna, Y. LeCun, A. Szlam and P. Vandergheynst
  • Learning mixed-curvature representations in products of model spaces, A. Gu, F. Sala, B. Gunel and C. Ré
  • Face image matching using fractal dimension, A. Z. Kouzani, F. He and K. Sammut
  • Fractal dimension based texture analysis of digital images, P. Shanmugavadivu and V. Sivakumar

Participants’ choice for presentation:

  • Poincaré embeddings for learning hierarchical representations, M. Nickel and D. Kiela
  • Embedding text in hyperbolic spaces, B. Dhingra, C. J. Shallue, M. Norouzi, A. M. Dai and G. E. Dahl

Grading: Discussions + Reports + Presentation