Vincent Gripon's Homepage

Research and Teaching Blog

Matching Convolutional Neural Networks without Priors about Data

C. E. R. K. Lassance, J. Vialatte and V. Gripon, "Matching Convolutional Neural Networks without Priors about Data," in Proceedings of Data Science Workshop, 2018. Submitted to.

We propose an extension of Convolutional Neural Networks (CNNs) to graph-structured data, including strided convolutions and data augmentation on graphs. Our method matches the accuracy of state-of-the-art CNNs when applied on images, without any prior about their 2D regular structure. On fMRI data, we obtain a significant gain in accuracy compared with existing graph-based alternatives.

Download manuscript.

Bibtex
@inproceedings{LasViaGri2018,
  author = {Carlos Eduardo Rosar Kos Lassance and
Jean-Charles Vialatte and Vincent Gripon},
  title = {Matching Convolutional Neural Networks
without Priors about Data},
  booktitle = {Proceedings of Data Science Workshop},
  year = {2018},
  note = {Submitted to},
}




You are the 602824th visitor

Vincent Gripon's Homepage