This paper reviews recent studies in emerging directions of understanding neural-network representations and learning neural networks with interpretable/disentangled middle-layer representations. Although deep neural networks have exhibited superior performance in various tasks, the interpretability is always an Achilles' heel of deep neural networks. At present, deep neural networks obtain a h...

Deep convolutional neural networks follow roughly the architecture of biological visual systems, and have shown a performance comparable to human observers in object recognition tasks. In this study, I test a pretrained deep neural network in some classic visual search tasks. The results reveal a qualitative difference from human performance. It appears that there is no difference between searc...

This paper presents a novel ensemble framework to extract highly discriminative feature representation of image and its application for group-level happpiness intensity prediction in wild. In order to generate enough diversity of decisions, n convolutional neural networks are trained by bootstrapping the training set and extract n features for each image from them. A recurrent neural network (R...

This paper describes our automatic speech recognition system for IWSLT2014 evaluation campaign. The system is based on weighted finite-state transducers and a combination of multiple subsystems which consists of four types of acoustic feature sets, four types of acoustic models, and Ngram and recurrent neural network language models. Compared with our system used in last year, we added addition...

Deep neural networks have demonstrated very promising performance on accurate segmentation of challenging organs (e.g., pancreas) in abdominal CT and MRI scans. The current deep learning approaches conduct pancreas segmentation by processing sequences of 2D image slices independently through deep, dense per-pixel masking for each image, without explicitly enforcing spatial consistency constrain...

In this work we report on progress in integrating deep convolutional features with Deformable Part Models (DPMs). We substitute the Histogram-of-Gradient features of DPMs with Convolutional Neural Network (CNN) features, obtained from the top-most, fifth, convolutional layer of Krizhevsky’s network [8]. We demonstrate that we thereby obtain a substantial boost in performance (+14.5 mAP) when co...

AC Accuracy ADL Activities of daily living AF Average F-measure CNN Convolutional neural network CPU Central processing unit DBN Deep belief network DT Decision tree HA Hand Gesture HAR Human activity recognition KNN K-nearest neighbors LSTM Longand short-term memory MV Means and variance NB Naive Bayes NF Normalized F-measure OAR Opportunity activity recognition RAM Random access memory ReLU R...

Recent advances in deep learning for object recognition in natural images has prompted a surge of interest in applying a similar set of techniques to medical images. Most of the initial attempts largely focused on replacing the input to such a deep convolutional neural network from a natural image to a medical image. This, however, does not take into consideration the fundamental differences be...

Deep learning (DL) based semantic segmentation methods have been providing state-of-the-art performance in the last few years. More specifically, these techniques have been successfully applied to medical image classification, segmentation, and detection tasks. One deep learning technique, U-Net, has become one of the most popular for these applications. In this paper, we propose a Recurrent Co...