English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Finding suitable features has been an essential problem in computer vision.We focus on Restricted Boltzmann Machines (RBMs), which, despite theirversatility, cannot accommodate transformations that may occur in the scene. Asa result, several approaches have been proposed that consider a set oftransformations, which are used to either augment the training set or transformthe actual learned filters. In this paper, we propose the ExplicitRotation-Invariant Restricted Boltzmann Machine, which exploits priorinformation coming from the dominant orientation of images. Our model extendsthe standard RBM, by adding a suitable number of weight matrices, associatedwith each dominant gradient. We show that our approach is able to learnrotation-invariant features, comparing it with the classic formulation of RBMon the MNIST benchmark dataset. Overall, requiring less hidden units, ourmethod learns compact features, which are robust to rotations.

Rotation-Invariant Restricted Boltzmann Machine Using Shared Gradient Filters