A Simple End-to-end Deep Reinforcement Learning Method for Situation Calculus – We propose a novel neural model for action recognition and action planning, in which information is encoded explicitly by the task-oriented context of the scene. The structure of the context is modeled by a pair of temporal- and spatial-dependent neural networks. As the task-oriented context of the scene plays a key role in the learned performance, this model achieves state-of-the-art results in both datasets.

In this paper, we propose a general framework to learn an objective function for action recognition and planning using convolutional neural networks. We show how to extract features of the objective function in the training set of such networks. We also show that the learning of feature maps of the objective function is a crucial step for a successful decision making problem. In doing so, we show how to make use of the available information in a supervised learning setting to learn a discriminative objective function. Our training data are shown to be rich in semantic information and we show how to use state-of-the-art image-level classification techniques to further improve the learning performance.

This paper investigates the problem of finding a linear model from the high-dimensional data. A major problem in this domain is to find a high-dimensional data that is suitable for the distribution or model used. In this work, a novel model is considered. The proposed model is an instance of the mixed model and is used for finding the best model from high-dimensional data. To the best of our knowledge, no prior work has examined the problem in real data sets. This paper presents an empirical evaluation of the proposed model, and presents preliminary results of the empirical results.

A General Framework of Learning Attribute Similarity in Deep Neural Networks

A Unified Deep Learning Framework for Multi-object Tracking

A Simple End-to-end Deep Reinforcement Learning Method for Situation Calculus

Robust Learning of Spatial Context-Dependent Kernels

The M1 Gaussian mixture model is Fisher-attenuatedThis paper investigates the problem of finding a linear model from the high-dimensional data. A major problem in this domain is to find a high-dimensional data that is suitable for the distribution or model used. In this work, a novel model is considered. The proposed model is an instance of the mixed model and is used for finding the best model from high-dimensional data. To the best of our knowledge, no prior work has examined the problem in real data sets. This paper presents an empirical evaluation of the proposed model, and presents preliminary results of the empirical results.