Jonathan Masci

Research

My research interests are:

  • Deep-Learning
  • Machine Learning
  • Computer Vision
  • Information Retrieval
  • Programming languages and compilers
  • Shape Analysis

me

During my Ph.D. I worked on deep-learning tehcniques for classification and detection of steel defects. The work was done in collaboration with ArcelorMittal and Centre for Mathematical Morphology of ParisTech.

I am an expert in convolutional-based neural networks and I am deeply interested in their extensions to narrow the gap between computer vision and machine learning.

I am also very interested in metric learning problems, especially in the setting of similarity-sensitive hashing to which I brought deep-learning for the first time. I proposed an extension of the siamese framework (DrLim) to produce binary representations and also a coupled version of the framework to address the multimodal case.

I am recently into Shape Analysis, so come back for some ineresting and "deep" news!