Multi-view Graph Convolutional Neural Network – Many recent methods for deep reinforcement learning (RL) rely on the use of multi-dimensional convolutional neural networks. This paper investigates the use of multi-dimensional convolutional neural networks (MDS-NNs) for non-linear reinforcement learning (NRL) tasks. We present a novel approach that employs convolutional networks for nonlinear RL tasks, which, by a neural network’s own, leads to efficient policy learning that avoids the need for costly re-training. We show that a nonlinear RL task may be more suited to a multi-dimensional MDS-NN, as it has a fully-connected network with an input manifold and a policy space. Moreover, we show that a nonlinear RL task (e.g., a simple image navigation task) may be more attractive to a multi-dimensional MDS-NN than a simple image detection task. Moreover, we obtain efficient policies for a simple RL task as a result of our approach.
In the present paper we study learning-based deep model for sentiment-based text classification. This approach employs supervised learning, which is a challenging machine learning problem. We address this issue by applying a method based on LSTM, which is not only very effective in learning state-of-the-art models on text classification tasks, but also in using supervised learning. We use the supervised learning technique of LSTM as the neural network structure to learn a model structure for this text classification task. Experiments on standard datasets demonstrate that the LSTM-based text classification models can outperform the state-of-the-art models on text classification tasks in terms of accuracy.
Fast and reliable indexing with dense temporal-temporal networks
Fusing Depth Colorization and Texture Coding to Decolorize Scenes
Multi-view Graph Convolutional Neural Network
Proxnically Motivated Multi-modal Transfer Learning from Imbalanced Data
The Classification of Text, the Brain, and Information Chain for Human-Robot CollaborationIn the present paper we study learning-based deep model for sentiment-based text classification. This approach employs supervised learning, which is a challenging machine learning problem. We address this issue by applying a method based on LSTM, which is not only very effective in learning state-of-the-art models on text classification tasks, but also in using supervised learning. We use the supervised learning technique of LSTM as the neural network structure to learn a model structure for this text classification task. Experiments on standard datasets demonstrate that the LSTM-based text classification models can outperform the state-of-the-art models on text classification tasks in terms of accuracy.