Deep Recurrent Neural Networks (RNNs) achieve state-of-the-art results in many sequence-to-sequence tasks. However, deep RNNs are difficult to train and suffer from overfitting. We introduce a training method that trains the network gradually, and treats each layer individually, to achieve improved results in language modelling tasks. Training deep LSTM with Gradual Learning (GL) obtains perple...

The last half-decade has seen a surge in deep learning research on irregular domains and efforts to extend convolutional neural networks (CNNs) work irregularly structured data. graph emerged as particularly useful geometrical object learning, able represent variety of well. Graphs can various complex systems, from molecular structure, computer social traffic networks. Consequent the extension ...

We present Earliness-Aware Deep Convolutional Networks (EA-ConvNets), an end-to-end deep learning framework, for early classification of time series data. Unlike most existing methods for early classification of time series data, that are designed to solve this problem under the assumption of the availability of a good set of pre-defined (often hand-crafted) features, our framework can jointly ...

Deep generative models parameterized by neural networks have recently achieved state-ofthe-art performance in unsupervised and semisupervised learning. We extend deep generative models with auxiliary variables which improves the variational approximation. The auxiliary variables leave the generative model unchanged but make the variational distribution more expressive. Inspired by the structure...