TY  - CHAP
T2  - Artificial Neural Networks and Machine Learning ? ICANN 2016 25th. International Conference on Artificial Neural Networks, Barcelona, Spain, September 6-9, 2016, Proceedings, Part II
PB  - Springer International Publishing
A1  - Giuffrida, Mario Valerio
A1  - Tsaftaris, Sotirios A.
UR  - http://dx.doi.org/10.1007/978-3-319-44781-0_57
Y1  - 2016///
TI  - Rotation-Invariant Restricted Boltzmann Machine Using Shared Gradient Filters
SP  - 480
N2  - Finding suitable features has been an essential problem in computer vision. We focus on Restricted Boltzmann Machines (RBMs), which, despite their versatility, cannot accommodate transformations that may occur in the scene. As a result, several approaches have been proposed that consider a set of transformations, which are used to either augment the training set or transform the actual learned filters. In this paper, we propose the Explicit Rotation-Invariant Restricted Boltzmann Machine, which exploits prior information coming from the dominant orientation of images. Our model extends the standard RBM, by adding a suitable number of weight matrices, associated with each dominant gradient. We show that our approach is able to learn rotation-invariant features, comparing it with the classic formulation of RBM on the MNIST benchmark dataset. Overall, requiring less hidden units, our method learns compact features, which are robust to rotations.
T3  - Lecture Notes in Computer Science
ID  - eprints3594
EP  - 488
SN  - 978-3-319-44780-3
AV  - none
ER  -