Interactive Stochastic Learning – The success of deep reinforcement learning (RL) is largely due to the high computational cost of the RL algorithms. In this paper we compare the effectiveness of a well-known RL algorithm named Long Short-Term Memory (LSTM) with an expensive RL algorithm. We propose an efficient RL algorithm called Long Short-Term Memory RL (LSTM-RL), and show that LSTM-RL outperforms the current state-of-the-art RL methods for various tasks. We also show that it is a good value for evaluating RL algorithms in terms of the efficiency.

We show that a simple spatial-temporal semantic segmentation method can outperform a state-of-the-art supervised segmentation approach. In this paper, we propose a novel semi-supervised segmentation approach to improve the performance of semantic segmentation, and we show that our approach can capture the semantic changes with a spatial-temporal similarity measure that can provide a better comparison between different approaches.

A Structural Recurrent Encoder

Towards a New Interpretation of Random Forests

Interactive Stochastic Learning

Learning to detect different types of malaria parasites in natural and artificial lighting systems

Unifying Spatial-Temporal Homology and Local Surface Statistical Mapping for 6D Object ClusteringWe show that a simple spatial-temporal semantic segmentation method can outperform a state-of-the-art supervised segmentation approach. In this paper, we propose a novel semi-supervised segmentation approach to improve the performance of semantic segmentation, and we show that our approach can capture the semantic changes with a spatial-temporal similarity measure that can provide a better comparison between different approaches.