Does fragile co-adaptation occur in small datasets?
Akbar Gumbira , Rajmund Kożuszek
AbstractRecent study using AlexNet architecture and ImageNet dataset has shown that the transferability of each layer in Convolutional Neural Network (CNN) can be quantified. One interesting finding from this study is that performance degradation when performing transfer learning without finetuning is not only caused by the specificity of the features, but also due to fragile co-adapted neurons between neighboring layers. This raises a question whether this phenomenon also occurs on smaller datasets and simpler network architectures. Using CIFAR-10 and three different CNN architectures, we reported that we have not seen this effect. The drop in performance is solely due to the specificity of the features learned for the source task.
|Publication size in sheets||0.5|
|Book||Proceedings of the Baltic URSI Symposium supported by National Committees of the Baltic Countries, vol. CFP18N89-ART, 2018, IEEE, ISBN 978-83-949421-3-7, 300 p.|
|Keywords in English||transfer learning, fragile co-adaptation, convolutional neural network|
|project||Development of new algorithms in the areas of software and computer architecture, artificial intelligence and information systems and computer graphics . Project leader: Arabas Jarosław,
, Phone: +48 22 234 7432, start date 01-06-2017, end date 31-10-2018, II/2017/DS/1, Completed
|Score|| = 15.0, BookChapterMatConf|
= 15.0, BookChapterMatConf
* presented citation count is obtained through Internet information analysis and it is close to the number calculated by the Publish or Perish system.