The automatic detection and classification of social signals is an important task, given the fundamental role nonverbal behavioral cues play in human communication. We present the first cross-lingual study on the detection of laughter and fillers in conversational and spontaneous speech collected ‘in the wild’ over IP (internet protocol). Further, this is the first comparison of LSTM and GRU ne...

In this work we present a step-by-step implementation of training a Language Model (LM) , using Recurrent Neural Network (RNN) and pre-trained GloVe word embeddings, introduced by Pennigton et al. in [1]. The implementation is following the general idea of training RNNs for LM tasks presented in [2] , but is rather using Gated Recurrent Unit (GRU) [3] for a memory cell, and not the more commonl...

In this project, we systematically analyze a deep neural networks based image caption generation method. With an image as the input, the method can output an English sentence describing the content in the image. We analyze three components of the method: convolutional neural network (CNN), recurrent neural network (RNN) and sentence generation. By replacing the CNN part with three state-of-the-...

Deep Q-learning is investigated as an end-to-end solution to estimate the optimal strategies for acting on time series input. Experiments are conducted on two idealized trading games. 1) Univariate: the only input is a wave-like price time series, and 2) Bivariate: the input includes a random stepwise price time series and a noisy signal time series, which is positively correlated with future p...

This paper presents a model based on Deep Learning algorithms of LSTM and GRU for facilitating an anomaly detection in Large Hadron Collider superconducting magnets. We used high resolution data available in Post Mortem database to train a set of models and chose the best possible set of their hyper-parameters. Using Deep Learning approach allowed to examine a vast body of data and extract the ...

Prediksi harga emas sangat penting karena menjadi acuan bagi para investor untuk menentukan strategi yang tepat dalam berinvestasi. Tren metode prediksi beberapa tahun terakhir adalah deep learning, merupakan subbidang machine learning dan populer menangani masalah time-series. Dalam penelitian ini, kami membandingkan performa dua model yaitu Long Short-Tern Memory (LSTM) Gated Recurrent Unit (...

Machine translation aims to translate text from a specific language into another using computer software. In this work, we performed neural machine with attention implementation on English-Malay parallel corpus. We attempt improve the model performance by rectified linear unit (ReLU) alignment. Different sequence-to-sequence models were trained. These include long-short term memory (LSTM), gate...

Gated Recurrent Unit (GRU) is a recently published variant of the Long Short-Term Memory (LSTM) network, designed to solve the vanishing gradient and exploding gradient problems. However, its main objective is to solve the long-term dependency problem in Recurrent Neural Networks (RNNs), which prevents the network to connect an information from previous iteration with the current iteration. Thi...