Collaborative resource scheduling between edge terminals and cloud centers is regarded as a promising means of effectively completing computing tasks and enhancing quality of service. In this paper, to further improve the achievable performance, the edge cloud resource scheduling (ECRS) problem is transformed into a multi-objective Markov decision process based on task dependency and features extraction. A multi-objective ECRS model is proposed by considering the task completion time, cost, energy consumption and system reliability as the four objectives. Furthermore, a hybrid approach based on deep reinforcement learning (DRL) and multi-objective optimization are employed in our work. Specifically, DRL preprocesses the workflow, and a multi-objective optimization method strives to find the Pareto-optimal workflow scheduling decision. Various experiments are performed on three real data sets with different numbers of tasks. The results obtained demonstrate that the proposed hybrid DRL and multi-objective optimization design outperforms existing design approaches.

Sentiment classification for reviews has attracted increasingly more attention from the Natural Language Processing (NLP) community. By embedding prior knowledge into learning structures, classifiers often achieve better performance than original methods. In this paper, we propose a sophisticated algorithm based on deep learning and information geometry in which the distribution of all training samples in the space is treated as prior knowledge and is encoded by Deep Belief Networks (DBN). From the view of information geometry, we construct the geodesic distance between the distributions over the features for classification. The study of the distributions contributes to the training of the DBN since the distance is correlated to the error rate in the classification. Finally, we evaluate our proposal using empirical data sets that are dedicated for sentiment classification. The results show that our algorithm results in a significant improvement over existing methods.