Improved weight initialization for deep and narrow feedforward neural network.

Appropriate weight initialization settings, along with the ReLU activation function, have become cornerstones of modern deep learning, enabling the training and deployment of highly effective and efficient neural network models across diverse areas of artificial intelligence. The problem of "dying ReLU," where ReLU neurons become inactive and yield zero output, presents a significant challenge in the training of deep neural networks with ReLU activation function. Theoretical research and various methods have been introduced to address the problem.

Contagion dynamics in time-varying metapopulation networks with node's activity and attractiveness.

The metapopulation network model is a mathematical framework used to study the spatial spread of epidemics with individuals' mobility. In this paper, we develop a time-varying network model in which the activity of a population is correlated with its attractiveness in mobility. By studying the spreading dynamics of the SIR (susceptible-infectious-recovered)-type disease in different correlated networks based on the proposed model, we theoretically derive the mobility threshold and numerically observe that increasing the correction between activity and attractiveness results in a reduced mobility threshold but suppresses the fraction of infected subpopulations.