Convolutional Neural Networks (CNNs) have achieved comparable error rates to well-trained human on ILSVRC2014 image classification task. To achieve better performance, the complexity of CNNs is continually increasing with deeper and bigger architectures. Though CNNs achieved promising external classification behavior, understanding of their internal work mechanism is still limited. In this work...

We improve automatic correction of grammatical, orthographic, and collocation errors in text using a multilayer convolutional encoder-decoder neural network. The network is initialized with embeddings that make use of character Ngram information to better suit this task. When evaluated on common benchmark test data sets (CoNLL-2014 and JFLEG), our model substantially outperforms all prior neura...

Convolutional neural networks have recently gained traction as a deep learning method for a variety of multidimensional, spatial processing problems. A myriad of architectures and applications exist and it can be daunting for the uninitiated to approach the subject. This survey paper seeks to provide a primer on Convolutional neural networks particularly within the fields of Earth and Ocean Sci...

We propose a new way of incorporating temporal information present in videos into Spatial Convolutional Neural Networks (ConvNets) trained on images, that avoids training SpatioTemporal ConvNets from scratch. We describe several initializations of weights in 3D Convolutional Layers of Spatio-Temporal ConvNet using 2D Convolutional Weights learned from ImageNet. We show that it is important to i...

In this study we propose a Convolutional Neural Network(CNN) which can classify hand drawn sketch images. Though CNN is known to be very effective on classification of realistic images, there are few studies on CNN dealing with nonphotorealistic images and even more images those types are mixing. Classifying non-photorealistic images is difficult mainly because there are no large datasets. In t...

This paper addresses the challenge of establishing a bridge between deep convolutional neural networks and conventional object detection frameworks for accurate and efficient generic object detection. We introduce Dense Neural Patterns, short for DNPs, which are dense local features derived from discriminatively trained deep convolutional neural networks. DNPs can be easily plugged into convent...

Inspired by the adequacy of convolutional neural networks in implicit extraction of visual features and the efficiency of Long Short-Term Memory Recurrent Neural Networks in dealing with long-range temporal dependencies, we propose a Convolutional Long Short-Term Memory Recurrent Neural Network (CNNLSTM) for the problem of dynamic gesture recognition. The model is able to successfully learn ges...

We propose a convolutional recurrent neural network, with Winner-Take-All dropout for high dimensional unsupervised feature learning in multi-dimensional time series. We apply the proposedmethod for object recognition with temporal context in videos and obtain better results than comparable methods in the literature, including the Deep Predictive Coding Networks previously proposed by Chalasani...

Deep convolutional neural networks contain tens of millions of parameters, making them impossible to work efficiently on embedded devices. We propose iterative approach of applying low-rank approximation to compress deep convolutional neural networks. Since classification and object detection are the most favored tasks for embedded devices, we demonstrate the effectiveness of our approach by co...