Convolutional neural networks (CNNs) have been successfully applied to many tasks such as digit and object recognition. Using convolutional (tied) weights significantly reduces the number of parameters that have to be learned, and also allows translational invariance to be hard-coded into the architecture. In this paper, we consider the problem of learning invariances, rather than relying on ha...

This paper describes the approaches used by our team (MultiBrasil) for the Multimedia Satellite Task at MediaEval 2017. For both disaster image retrieval and flood-detection in satellite images, we employ neural networks for end-to-end learning. Specifically, for the first subtask, we exploit Convolutional Networks and Relation Networks while, for the latter, dilated Convolutional Networks were...

Quantum-inspired artificial neural network is an interesting research area, which combines quantum computing and deep learning. Several models of quantum-inspired neuron with real-valued weights have been proposed, they were mainly used to build the three-layer feedforward networks. In this work, we improve convolutional networks (CNNs) by utilizing way data representation operation. Specifical...

Building large models with parameter sharing accounts for most of the success of deep convolutional neural networks (CNNs). In this paper, we propose doubly convolutional neural networks (DCNNs), which significantly improve the performance of CNNs by further exploring this idea. In stead of allocating a set of convolutional filters that are independently learned, a DCNN maintains groups of filt...

In this work, we propose a new algorithm for boosting Deep Convolutional Neural Networks (BoostCNN) to combine the merits of boosting and modern neural networks. To learn this new model, we propose a novel algorithm to incorporate boosting weights into the deep learning architecture based on least squares objective function. We also show that it is possible to use networks of different structur...

Convolutional Neural Networks (CNNs) have recently emerged as the dominant model in computer vision. If provided with enough training data, they predict almost any visual quantity. In a discrete setting, such as classification, CNNs are not only able to predict a label but often predict a confidence in the form of a probability distribution over the output space. In continuous regression tasks,...