Search

In this paper, a novel loss function is proposed to measure the correlation among different learning tasks and select useful feature components for each classification task. Firstly, the knowledge map we proposed is used for organizing the affiliation relationship between objects in natural world. Secondly, a novel loss function-orthogonality loss is proposed to make the deep features more discriminative by removing useless feature components. Furthermore, in order to prevent the extracted feature maps from being too divergent and causing over-fitting which will reduce network performance, this paper also added the orthogonal distribution regularization term to constrain the distribution of network parameters. Finally, the proposed orthogonality loss is applied in a multi-task network structure to learn more discriminative deep feature, and also to evaluate the validity of the proposed loss function.The results show that compared with the traditional deep convolutional neural network and a multi-task network without orthogonality loss, the multi -task based orthogonality loss is significantly better than the other two types of networks on image classification.

The activation of Ras small GTPases, including RalA and RalB, plays an important role in carcinogenesis, tumor progress, and metastasis. In the current study, we report the discovery of a series of 6-sulfonylamide-pyrano [2,3-c]-pyrazole derivatives as novel RalA inhibitors. ELISA-based biochemical assay results indicated that compounds 4k–4r suppressed RalA/B binding capacities to their substrates. Cellular proliferation assays indicated that these RalA inhibitors potently inhibited the proliferation of HCC cell lines, including HepG2, SMMC-7721, Hep3B, and Huh-7 cells. Among the evaluated compounds, 4p displayed good inhibitory capacities on RalA (IC50 = 0.22 μM) and HepG2 cells (IC50 = 2.28 μM). Overall, our results suggested that a novel small-molecule RalA inhibitor with a 6-sulfonylamide-pyrano [2, 3-c]-pyrazole scaffold suppressed autophagy and cell proliferation in hepatocellular carcinoma, and that it has potential for HCC-targeted therapy.

Based on the data of A-share listed companies in Shanghai and Shenzhen from 2013 to 2017 and the air quality monitoring data released by the China National Environmental Monitoring Centre, this paper conducts an empirical test on the relationship between air pollution and corporate cash holdings. The empirical research found that: first, air pollution increases the level of enterprise cash holdings. Second, there are some differences between heavily polluting and non-heavy polluting enterprises. The impact of air pollution is more significant in non-heavily polluting enterprises. Furthermore, the results show that the relationship between air pollution and cash holdings is significant regardless of the level of regional financial development. However, the influence of air pollution on cash holdings has a significant positive influence on nonstate-owned enterprises, while state-owned enterprises do not have such a significant impact. The research conclusions are conducive to revealing the relationship between the natural environment and micro-financial activities.