Using Support Vector Machines, Convolutional Neural Networks and Deep Belief Networks for Partially Occluded Object Recognition Joseph Lin Chu Artificial neural networks have been widely used for machine learning tasks such as object recognition. Recent developments have made use of biologically inspired architectures, such as the Convolutional Neural Network, and the Deep Belief Network. A the...

Convolutional network are the de-facto standard for analysing spatio-temporal data such as images, videos, 3D shapes, etc. Whilst some of this data is naturally dense (for instance, photos), many other data sources are inherently sparse. Examples include penstrokes forming on a piece of paper, or (colored) 3D point clouds that were obtained using a LiDAR scanner or RGB-D camera. Standard “dense...

Methods from convex optimization are widely used as building blocks for deep learning algorithms. However, the reasons for their empirical success are unclear, since modern convolutional networks (convnets), incorporating rectifier units and max-pooling, are neither smooth nor convex. Standard guarantees therefore do not apply. This paper provides the first convergence rates for gradient descen...

Owing to the use of nonlinear loads in distribution side, there are power quality issues such as voltage swell/sag, harmonics, flickers, imbalance, and outage. The harmonics system affect hence a suitable methodology is vital mitigate compensation reactive power. In this paper, CNN (Convolutional Neural Network)-based harmonic mitigation performed. A 5-level cascaded H-bridge inverter employed ...

In this work, we address the face parsing task with a Fully-Convolutional continuous CRF Neural Network (FCCNN) architecture. In contrast to previous face parsing methods that apply region-based subnetwork hundreds of times, our FCCNN is fully convolutional with high segmentation accuracy. To achieve this goal, FC-CNN integrates three subnetworks, a unary network, a pairwise network and a conti...

Brain tumor segmentation in magnetic resonance imaging (MRI) is helpful for diagnostics, growth rate prediction, tumor volume measurements and treatment planning of brain tumor. The difficulties for brain tumor segmentation are mainly due to high variation of brain tumors in size, shape, regularity, location, and their heterogeneous appearance (e.g., contrast, intensity and texture variation fo...

We derive a relationship between network representation in energy-efficient neuromorphic architectures and block Toplitz convolutional matrices. Inspired by this connection, we develop deep convolutional networks using a family of structured convolutional matrices and achieve state-of-the-art trade-off between energy efficiency and classification accuracy for well-known image recognition tasks....

Eric O. Postma1, H. Jaap van den Herik1, and Patrick T.W. Hudson1 Abstract. A model for attentional scanning is constructed in the form of a gating network which consists of gating lattices. A gating lattice is a sparsely-connected neural network. The process of covert attention is interpreted as a biological solution to the problem of translation-invariant pattern processing. We arrive at the ...

The relationship between objects can be described from different angles. Although multiple kinds of relationships make the connections complex, they bring in more discriminative information for clustering tasks. Therefore, how to effectively fuse becomes a critical problem. In this paper, we propose novel Multi-graph Convolutional Clustering Network which deeply explores feature nodes and fuses...

Abstract The process of parametric equalization musical pieces seeks to highlight their qualities by cutting and/or stimulating certain frequencies. In this work, we present a neural model capable equalizing song according the genre that is being played at given moment. It normal (1) should adapt throughout and not always be same for whole song; (2) songs do belong specific may contain touches ...