1. Paper (LaTex)
  2. Code (IPython notebooks)
  3. Results (IPython notebooks)


  1. Algorithm derivation: from sparse coding to encoder learning through dictionary learning
  2. Implementation of our auto-encoder model
  3. Learning Gabor filters from image data
  4. Solver comparison (with Xavier matlab primal-dual formulation)
  5. Genre recognition
    1. GTZAN
    2. pre-processing
    3. graph construction
    4. feature extraction
    5. classification
  6. An experiment launcher which allows to test the influence of an hyper-parameter on various metrics.


See the experiments.

Michaël Defferrard

I am currently pursuing master studies in Information Technologies at EPFL. My master project, conducted at the LTS2 Signal Processing laboratory led by Prof. Pierre Vandergheynst, is about audio classification with structured deep learning. I previously devised an image inpainting algorithm. It used a non-local patch graph representation of the image and a structure detector which leverages the graph representation and influences the fill-order of the exemplar-based algorithm. I've been a Research Assistant in the lab, where I did investigate Super Resolution methods for Mass Spectrometry. I develop PyUNLocBoX, a convex optimization toolbox in Python.

Leave a Reply