On the Layer Selection in Small-Scale Deep Networks
Muravev,Anton; Raitoharju,Jenni; Gabbouj,Moncef (2018-11)
11 / 2018
2018 7th European Workshop on Visual Information Processing (EUVIP)
This publication is copyrighted. You may download, display and print it for Your own personal use. Commercial use is prohibited
Julkaisun pysyvä osoite on
Deep learning algorithms (in particular Convolutional Neural Networks, or CNNs) have shown their superiority in computer vision tasks and continue to push the state of the art in the most difﬁcult problems of the ﬁeld. However, deep models frequently lack interpretability. Current research efforts are often focused on increasingly complex and computationally expensive structures. These can be either handcrafted or generated by an algorithm, but in either case the speciﬁc choices of individual structural elements are hard to justify. This paper aims to analyze statistical properties of a large sample of small deep networks, where the choice of layer types is randomized. The limited representational power of such models forces them to specialize rather than generalize, resulting in several distinct structural patterns. Observing the empirical performance of structurally diverse weaker models thus allows for some practical insight into the connection between the data and the choice of suitable CNN architectures.
- TUNICRIS-julkaisut 
Näytetään aineisto, joilla on samankaltaisia nimekkeitä, tekijöitä tai asiasanoja.
Smirnov,Sergey; Gotchev,Atanas; Hannuksela,Miska
IEEE International Conference on Multimedia and Expo (2013)
Joint de-noising and fusion of 2D video and depth map sequences sensed by low-powered tof range sensor Georgiev,Mihail; Gotchev,Atanas; Hannuksela,Miska
IEEE International Conference on Multimedia and Expo (Institute of Electrical and Electronics Engineers IEEE, 2013)
Georgiev,Mihail; Gotchev,Atanas; Hannuksela,Miska
IEEE International Symposium on Circuits and Systems (Institute of Electrical and Electronics Engineers IEEE, 2013)