Recently, it has been observed that when representations are learnt in a way that encourages sparsity, improved performance is obtained on classification tasks. These methods involve combinations of activation functions, sampling steps and different kinds of penalties. To investigate the effectiveness of sparsity by itself, we propose the “k sparse autoencoder”, which is an autoencoder with lin...

Inspired by enormous success of fully convolutional network (FCN) in semantic segmentation, as well as the similarity between semantic segmentation and pixel-by-pixel polarimetric synthetic aperture radar (PolSAR) image classification, exploring how to effectively combine the unique polarimetric properties with FCN is a promising attempt at PolSAR image classification. Moreover, recent research...

How do political institutions shape government size and redistributional policies? An empirical model proposes a possible framework to evaluate sign and magnitude of the relation. Political institutions are classified in complementary constraints, namely political competition, competition in executive recruitment and constraints on the executive. Results show that the stronger democratic instit...

This paper addresses the land cover classification task for remote sensing images by deep self-taught learning. Our selftaught learning approach learns suitable feature representations of the input data using sparse representation and undercomplete dictionary learning. We propose a deep learning framework which extracts representations in multiple layers and use the output of the deepest layer ...