skip to content

Faculty of Mathematics

 

 

Career

  • 2021-now: Postdoctoral research associate in the Cambridge Image Analysis group,
  • 2016-2021: PhD in applied mathematics, in the Cambridge Image Analysis group,
  • 2015-2016: Part III, focused on statistics and applied analysis,
  • 2012-2015: Undergraduate degrees in mathematics and physics.

Research

My main research interest is in studying how to build principled (i.e. incorporating desired symmetries, robustness etc.) machine learning and deep learning approaches to solving ill-posed inverse problems, such as those which arise in medical image reconstruction (e.g. MRI and CT). Much of my work in this direction draws inspiration from structure-preserving numerical methods. Besides this I have a broad interest in applied mathematics in general.

Publications

Hamiltonian Matching for Symplectic Neural Integrators
P Canizares, D Murari, C-B Schönlieb, F Sherry, Z Shumaylov
(2024)
Lie Algebra Canonicalization: Equivariant Neural Operators under arbitrary Lie Groups
Z Shumaylov, P Zaika, J Rowbottom, F Sherry, M Weber, C-B Schönlieb
(2024)
Convergent Regularization in Inverse Problems and Linear Plug-and-Play Denoisers
A Hauptmann, S Mukherjee, CB Schönlieb, F Sherry
– Foundations of Computational Mathematics
(2024)
1
Designing stable neural networks using convex analysis and ODEs
F Sherry, E Celledoni, MJ Ehrhardt, D Murari, B Owren, CB Schönlieb
– Physica D : Non-linear phenomena
(2024)
463,
134159
Dynamical Systems–Based Neural Networks
E Celledoni, D Murari, B Owren, CB Schonlieb, F Sherry
– SIAM Journal on Scientific Computing
(2023)
45,
a3071
Resilient Graph Neural Networks: A Coupled Dynamical Systems Approach
M Eliasof, D Murari, F Sherry, C-B Schönlieb
(2023)
Convergent regularization in inverse problems and linear plug-and-play denoisers
A Hauptmann, S Mukherjee, C-B Schönlieb, F Sherry
(2023)
Designing Stable Neural Networks using Convex Analysis and ODEs
F Sherry, E Celledoni, MJ Ehrhardt, D Murari, B Owren, C-B Schönlieb
(2023)
Imaging With Equivariant Deep Learning: From unrolled network design to fully unsupervised learning
D Chen, M Davies, MJ Ehrhardt, CB Schonlieb, F Sherry, J Tachella
– IEEE Signal Processing Magazine
(2023)
40,
134
Dynamical systems' based neural networks
E Celledoni, D Murari, B Owren, C-B Schönlieb, F Sherry
(2022)
  • 1 of 2
  • >

Research Group

Cambridge Image Analysis

Personal homepage