It is well known that metamodel or surrogate modeling techniques have been widely applied in engineering problems due to their higher efficiency. However, with the increase of the linearity and dimensions, it is difficult for the present popular metamodeling techniques to construct reliable metamodel and apply to more and more complicated high dimensional problems. Recently, neural networks (NN...

Deep convolutional neural networks (CNNs) have greatly improved the Face Recognition (FR) performance in recent years. Almost all CNNs in FR are trained on the carefully labeled datasets containing plenty of identities. However, such high-quality datasets are very expensive to collect, which restricts many researchers to achieve state-of-the-art performance. In this paper, we propose a framewor...

We analyze the expressiveness and loss surface of practical deep convolutional neural networks (CNNs) with shared weights. We show that such CNNs produce linearly independent features (and thus linearly separable) at every “wide” layer which has more neurons than the number of training samples. This condition holds e.g. for the VGG network. Furthermore, we provide for such wide CNNs necessary a...

Connectionist temporal classification (CTC) is a popular sequence prediction approach for automatic speech recognition that is typically used with models based on recurrent neural networks (RNNs). We explore whether deep convolutional neural networks (CNNs) can be used effectively instead of RNNs as the “encoder” in CTC. CNNs lack an explicit representation of the entire sequence, but have the ...

D eep learning methods are used on spectroscopic data to predict drug content in tablets from near infrared (NIR) spectra. Using convolutional neural networks (CNNs), features are extracted from the spectroscopic data. Extended multiplicative scatter correction (EMSC) and a novel spectral data augmentation method are benchmarked as preprocessing steps. The learned models perform better or on pa...

In this paper, we present a robust method for scene recognition, which leverages Convolutional Neural Networks (CNNs) features and Sparse Coding setting by creating a new representation of indoor scenes. Although CNNs highly benefited the fields of computer vision and pattern recognition, convolutional layers adjust weights on a globalapproach, which might lead to losing important local details...

Traditional approaches to the task of ACE event extraction are either the joint model with elaborately designed features which may lead to generalization and data-sparsity problems, or the word-embedding model based on a twostage, multi-class classification architecture, which suffers from error propagation since event triggers and arguments are predicted in isolation. This paper proposes a nov...

Recently, convolutional neural networks (CNNs) have been used as a powerful tool to solve many problems of machine learning and computer vision. In this paper, we aim to provide insight on the property of convolutional neural networks, as well as a generic method to improve the performance of many CNN architectures. Specifically, we first examine existing CNN models and observe an intriguing pr...

Deep Convolutional Neural Networks (CNNs) are the state of the art systems for image classification and scene understating. However, such techniques are computationally intensive and involve highly regular parallel computation. CNNs can thus benefit from a significant acceleration in execution time when running on fine grain programmable logic devices. As a consequence, several studies have pro...

Deep convolutional neural networks (CNNs) have demonstrated impressive performance on visual object classification tasks. In addition, it is a useful model for predication of neuronal responses recorded in visual system. However, there is still no clear understanding of what CNNs learn in terms of visual neuronal circuits. Visualizing CNN’s features to obtain possible connections to neuronscien...