Deep Belief Networks (DBNs) have recently shown impressive performance on a broad
range of classification problems. Their generative properties allow better understanding of …

ABSTRACT Recently the 'Million Song Dataset', containing audio features and metadata for
one million songs, was made available. In this paper, we build a convolutional network that …

Background A living cell has a complex, hierarchically organized signaling system that
encodes and assimilates diverse environmental and intracellular signals, and it further …

In this paper, we propose a hybrid architecture that combines the image modeling strengths
of the bag of words framework with the representational power and adaptability of learning …

Spiking Neural Networks (SNNs) claim to present many advantages in terms of biological
plausibility and energy efficiency compared to standard Deep Neural Networks (DNNs) …

Recently, the coding of local features (eg SIFT) for image categorization tasks has been
extensively studied. Incorporated within the Bag of Words (BoW) framework, these …

We propose an automatic framework for quality assessment of a photograph as well as
analysis of its aesthetic attributes. In contrast to the previous methods that rely on manually …

The number of different modalities for remote sensors continues to grow, bringing with it an
increase in the volume and complexity of the data being collected. Although these datasets …

An important part of electronic dance music (EDM) is the so-called beat. It is defined by the
drum track of the piece and is a style defining element. While producing EDM, creating the …

Designing a principled and effective algorithm for learning deep architectures is a
challenging problem. The current approach involves two training phases: a fully …