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...

In this paper, we use variational recurrent neural network to investigate the anomaly detection problem on graph time series. The temporal correlation is modeled by the combination of recurrent neural network (RNN) and variational inference (VI), while the spatial information is captured by the graph convolutional network. In order to incorporate external factors, we use feature extractor to au...

When a neural language model is used for caption generation, the image information can be fed to the neural network either by directly incorporating it in a recurrent neural network – conditioning the language model by injecting image features – or in a layer following the recurrent neural network – conditioning the language model by merging the image features. While merging implies that visual...

Some results from a method for generating recurrent neural networks (RNN) for prediction of financial and macroeconomic time series are presented. In the presented method, a feedforward neural network (FFNN) is first obtained using backpropagation. While backpropagation is usually able to find a fairly good predictor, all FFNN are limited by their lack of short-term dynamic memory. RNNs, by con...

The success of sentence classification often depends on understanding both the syntactic and semantic properties of wordphrases. Recent progress on this task has been based on exploiting the grammatical structure of sentences but often this structure is difficult to parse and noisy. In this paper, we propose a structureindependent ‘Gated Representation Alignment’ (GRA) model that blends a phras...

Accurate estimation of regional wall thicknesses (RWT) of left ventricular (LV) myocardium from cardiac MR sequences is of significant importance for identification and diagnosis of cardiac disease. Existing RWT estimation still relies on segmentation of LV myocardium, which requires strong prior information and user interaction. No work has been devoted into direct estimation of RWT from cardi...

Automatic drum transcription is the process of generating symbolic notation for percussion instruments within audio recordings. To date, recurrent neural network (RNN) systems have achieved the highest evaluation accuracies for both drum solo and polyphonic recordings, however the accuracies within a polyphonic context still remain relatively low. To improve accuracy for polyphonic recordings, ...

Recurrent neural networks show state-of-theart results in many text analysis tasks but often require a lot of memory to store their weights. Recently proposed Sparse Variational Dropout (Molchanov et al., 2017) eliminates the majority of the weights in a feed-forward neural network without significant loss of quality. We apply this technique to sparsify recurrent neural networks. To account for...

This paper presents the Wind Energy Conversion System (WECS) combining Permanent Magnet Synchronous Generator (PMSG) with PSO-RNN controller. The proposed hybrid technique uses Particle Swarm Optimization (PSO) algorithm along with Recurrent Neural Network (RNN) which generates the optimal dc reference current. The proposed Maximum Power Point Tracking (MPPT) algorithm finds the maximum operati...

The paper proposed to use a Recurrent Neural Network model (RNN) for process prediction of the osmotic dehydration kinetics of nature product cubes (apple, sweet potatoes and potatoes) at different operational conditions of temperature and concentration of the osmotic solution. The proposed RNN model has five inputs, three outputs and eight neurons in the hidden layer, with global and local fee...