This paper presents different deep neural network architectures designed to forecast the distribution of returns on a portfolio of U.S. Treasury securities. A long short-term memory model and a convolutional neural network are tested as the main building blocks of each architecture. The models...

An overview of the current situation in the United States and a look to the future of low-level waste management are presented. Current problems and challenges are discussed, such as: the need of additional disposal sites in the future; risks and costs involved in transport of low-level wastes;...

The goal of this paper is to deliver to the reader a large number of graphs in order to allow him/her to choose the ones that he/she considers important to form his/her own opinion. Graphs from data are more important than statements which are mainly interpretation and political, but the problem...