In this paper, we propose a new unsupervised feature learning framework, namely Deep Sparse Coding (DeepSC), that extends sparse coding to a multi-layer architecture for visual object recognition tasks. The main innovation of the framework is that it connects the sparse-encoders from different layers by a sparse-to-dense module. The sparse-to-dense module is a composition of a local spatial poo...

The composition of services that are indexed in a large-scale service directory often involves many complex queries issued by the service composition algorithm to the directory. These queries may cause considerable processing effort within the directory, thus limiting scalability. In this paper we present a novel approach to increase scalability: The directory offers a compact digest that servi...

Wild ginger (Hedychium gardnerianum) is a tall rhizomatous herb that invades forests and shrubland fragments in northern New Zealand. In order to determine the impacts of this invasive weed on forest processes, comparisons of conifer-broadleaved forest patches with different densities of ginger were made at Opononi and Whangarei in Northland. Soil properties, vegetation structure, floristics, a...

The olfactory system removes correlations in natural odors using a network of inhibitory neurons in the olfactory bulb. It has been proposed that this network integrates the response from all olfactory receptors and inhibits them equally. However, how such global inhibition influences the neural representations of odors is unclear. Here, we study a simple statistical model of the processing in ...

The olfactory system removes correlations in natural odors using a network of inhibitory neurons in the olfactory bulb. It has been proposed that this network integrates the response from all olfactory receptors and inhibits them equally. However, how such global inhibition influences the neural representations of odors is unclear. Here, we study a simple statistical model of this situation, wh...

solving a large sparse set of linear equations is of the problems widely seen in every numerical investigation in the entire range of engineering disciplines. employing a finite element approach in solving partial derivative equations, the resulting stiffness matrices would contain many zero-valued elements. moreover, storing all these sparse matrices in a computer memory would slower the compu...

The main question of this paper is: What happens to sparse resultants under composition? More precisely, let f1, . . . , fn be homogeneous sparse polynomials in the variables y1, . . . , yn and g1, . . . , gn be homogeneous sparse polynomials in the variables x1, . . . , xn. Let fi ◦ (g1, . . . , gn) be the sparse homogeneous polynomial obtained from fi by replacing yj by gj . Naturally a quest...

Obesity is a known risk factor for the development of non-alcoholic fatty liver disease (NAFLD); however, it has been suggested that dietary fat, both amount and composition, may play a pivotal role in its development, independent of body fatness. Studies that have investigated the role of dietary fat on liver fat accumulation are reasonably sparse. We review here the available work that has in...