Matching Convolutional Neural Networks without Priors about Data

Add code
Feb 27, 2018
Carlos Eduardo Rosar Kos Lassance, Jean-Charles Vialatte, Vincent Gripon
Figure 1 for Matching Convolutional Neural Networks without Priors about Data
Figure 2 for Matching Convolutional Neural Networks without Priors about Data
Figure 3 for Matching Convolutional Neural Networks without Priors about Data
Figure 4 for Matching Convolutional Neural Networks without Priors about Data

Share this with someone who'll enjoy it:

Twitter IconFacebook IconLinkedin IconWhatsapp IconMessenger Icon

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.

View paper onarxiv icon

Share this with someone who'll enjoy it:

Twitter IconFacebook IconLinkedin IconWhatsapp IconMessenger Icon