Biomedical Imaging Group
Logo EPFL
    • Splines Tutorials
    • Splines Art Gallery
    • Wavelets Tutorials
    • Image denoising
    • ERC project: FUN-SP
    • Sparse Processes - Book Preview
    • ERC project: GlobalBioIm
    • The colored revolution of bioimaging
    • Deconvolution
    • SMLM
    • One-World Seminars: Representer theorems
    • A Unifying Representer Theorem
Follow us on Twitter.
Join our Github.
Masquer le formulaire de recherche
Menu
BIOMEDICAL IMAGING GROUP (BIG)
Laboratoire d'imagerie biomédicale (LIB)
  1. School of Engineering STI
  2. Institute IEM
  3.  LIB
  4.  ERC Project: FunLearn
  • Laboratory
    • Laboratory
    • Laboratory
    • People
    • Jobs and Trainees
    • News
    • Events
    • Seminars
    • Resources (intranet)
    • Twitter
  • Research
    • Research
    • Researchs
    • Research Topics
    • Talks, Tutorials, and Reviews
  • Publications
    • Publications
    • Publications
    • Database of Publications
    • Talks, Tutorials, and Reviews
    • EPFL Infoscience
  • Code
    • Code
    • Code
    • Demos
    • Download Algorithms
    • Github
  • Teaching
    • Teaching
    • Teaching
    • Courses
    • Student projects
  • Splines
    • Teaching
    • Teaching
    • Splines Tutorials
    • Splines Art Gallery
    • Wavelets Tutorials
    • Image denoising
  • Sparsity
    • Teaching
    • Teaching
    • ERC project: FUN-SP
    • Sparse Processes - Book Preview
  • Imaging
    • Teaching
    • Teaching
    • ERC project: GlobalBioIm
    • The colored revolution of bioimaging
    • Deconvolution
    • SMLM
  • Machine Learning
    • Teaching
    • Teaching
    • One-World Seminars: Representer theorems
    • A Unifying Representer Theorem

FunLearn

Functional Learning: From Theory to Application in Bioimaging

Principal Investigator: Prof. Michael Unser

Participants: Shayan Aziznejad, Thomas Debarre, Jonathan Dong, Sebastian Neumayer, Rahul Parhi, Thanh-An Pham, Mehrsa Pourya

Period: October 1, 2021 — September 30, 2026.

Abstract

While deep neural networks have shown a remarkable ability to reconstruct biomedical images, they also raise serious reservations that pertain to the stability of these tools and the extent to which one can trust their output. The main concern, which motivates this research program, is that it is very difficult to control their Lipschitz constant. This quantity measures the degree to which a small perturbation of the input can have a huge effect on the output. At worst, a network with a poor Lipschitz constant can be devastating in the context of image reconstruction.

We believe that better Lipschitz constants will result from much shallower neural architectures, which are easier to control. However, a reduction in the number of layers will degrade the performance, unless we augment the sophistication of the primary modules; in particular, the nonlinear ones. By drawing on our career-long experience with splines, we therefore propose to rely on the powerful tools of functional optimization to improve learning architectures. In particular, we shall investigate a variational formulation of robust learning that relies on a new HDTV criterion. It will allow us to develop two novel approaches to learning: sparse simplicial splines, and hierarchical spline networks—an extension of the popular deep ReLU neural networks.

In parallel, we shall develop specific neural networks to solve two outstanding problems:

  • a "best-of-both-worlds" approach to the reconstruction of biomedical images, involving the stable integration of state-of-the-art physics-based solvers with the new tools of machine learning;
  • the 3D reconstruction of the entire manifold of configurations of a biomolecule from a large collection of very low-dose cryo-electron tomograms. This goal, which may be viewed as the Graal of structural biology, has remained elusive so far and calls for an entirely new paradigm for single-particle analysis.

  • Laboratory
  • Research
    • Research Topics
    • Talks, Tutorials, and Reviews
  • Publications
  • Code
  • Teaching
Logo EPFL, Ecole polytechnique fédérale de Lausanne
Emergencies: +41 21 693 3000 Services and resources Contact Map Webmaster email

Follow EPFL on social media

Follow us on Facebook. Follow us on Twitter. Follow us on Instagram. Follow us on Youtube. Follow us on LinkedIn.
Accessibility Disclaimer Privacy policy

© 2023 EPFL, all rights reserved