Course enrollment recommendation is a relevant task that helps university students decide what is the best combination of courses to enroll in the next term. In particular, recommender system techniques like matrix factorization and collaborative filtering have been developed to try to solve this problem. As these techniques fail to represent the time-dependent nature of academic performance datasets we propose a deep learning approach using recurrent neural networks that aims to better represent how chronological order of course grades affects the probability of success. We have shown that it is possible to obtain a performance of 81.10% on AUC metric using only grade information and that it is possible to develop a recommender system with academic student performance prediction. This is shown to be meaningful across different student GPA levels and course difficulties

We study, through discrete element simulations, the discharge of granular materials through a circular orifice on the base of a cylindrical silo forced by a surcharge. At the beginning of the discharge, for a high granular column, the flow rate $Q_{\rm ini}$ scales as in the Beverloo equation for free discharge. However, we find that the flow rate $Q_{\rm end}$ attained at the end of the forced discharge scales as $\sqrt{\rho_b P}D_o^3/D_s$, with $\rho_b$ the bulk density, $P$ the pressure applied by the overweight, $D_o$ the orifice diameter and $D_s$ the silo diameter. We use the work$-$energy theorem to formulate an equation for the flow rate $Q_{\rm end}$ that predicts the scalings only in part. We discuss the new challenges offered by the phenomenology of strongly forced granular flows.

One of the most important debates is currently focusing on specifying the training that university teachers must receive for their professional practice. Improving it in higher education is extremely important not only for the scientific production generated by university but also for the adequacy of the training that future graduates will be offered; professionals facing an increasingly demanding labour market with new needs. University teachers training, thus, should be a priority in academic policies due to their influence and the role played in the evolution of society, as well as being the basis of the quality of Higher Education. This research, a case study in the State of Goias (Brazil), is focused on a sample of practicing university teachers from different fields of knowledge, and has as main objective to know the characteristics of the training received for their professional practice, both in the field of scientific education and their educational role and ability to transfer knowledge. The methodology used has been mixed, not experimental and descriptive, with the help of instruments for data collection and analysis of quantitative and qualitative nature (questionnaires, interviews, monitoring, checklists, documentary analysis, etc.). The results confirmed the initial hypothesis, which stated that university teachers current training is primarily scientific and technical, and has gaps in the teacher training required today for a more effective work in the classroom. In this area teachers often use teaching methodologies supported by previous experiences with traditional features. Finally, to optimize this situation, different strategies for university teachers training are proposed seeking to improve both their reflection and teaching practice.