Search

Neural networks have achieved dramatic improvements in recent years and depict the state-of-the-art methods for many real-world tasks nowadays. One drawback is, however, that many of these models are overparameterized, which makes them both computationally and memory intensive. Furthermore, overparameterization can also lead to undesired overfitting side-effects. Inspired by recently proposed magnitude-based pruning schemes and the Wald test from the field of statistics, we introduce a novel magnitude and uncertainty (MU) pruning criterion that helps to lessen such shortcomings. One important advantage of our MU pruning criterion is that it is scale-invariant, a phenomenon that the magnitude-based pruning criterion suffers from. In addition, we present a 'pseudo bootstrap' scheme, which can efficiently estimate the uncertainty of the weights by using their update information during training. Our experimental evaluation, which is based on various neural network architectures and datasets, shows that our new criterion leads to more compressed models compared to models that are solely based on magnitude-based pruning criteria, with, at the same time, less loss in predictive power.

UN Sustainable Development Goals and the Paris agreement for climate change indicate that a transition to sustainable and healthy diets is necessary. Additionally, the fact that agricultural sector is responsible for near a quarter of global greenhouse emissions (IPCC 2019-special report on climate change), such transition will require substantial dietary shifts, including reduction of sugar and red meat consumption. Vietnam, with more than 95 millions of population, have a challenge to significantly reduce the rice consumption and convert some of the land used for it to production of more legumes. However, correct allocation of arable land for cultivation of particular crops' combination that would ease the transition, and comply with recommendations for healthy nutritional intake, is a challenge of the society. We approached the problem of arable land allocation with mathematical optimization, in particular stochastic evolutionary computing. Arable land allocation to crops' combination is evaluated through three objectives: food self-sufficiency, climate efficiency and crop diversity. Candidate solutions (crops' combinations) were analysed through the non-dominated Pareto front with prioritizing the objective of food self-sufficiency of Vietnam. The results suggest significant change in production of certain crops. As such, sugar cane and rice are required to be reduced on expense of increased production of soybeans, maize, brassicas, and nuts. Therefore, the current surplus of produced carbohydrates would be reduced while proteins increased, which leads to balanced production of macronutrients.

The increasing liberalization of European electricity markets, the growing proportion of intermittent renewable energy being fed into the energy grids, and also new challenges in the patterns of energy consumption (such as electric mobility) require flexible and intelligent power grids capable of providing efficient, reliable, economical, and sustainable energy production and distribution. From the supplier side, particularly, the integration of renewable energy sources (e.g., wind and solar) into the grid imposes an engineering and economic challenge because of the limited ability to control and dispatch these energy sources due to their intermittent characteristics. Time-series prediction of wind speed for wind power production is a particularly important and challenging task, wherein prediction intervals (PIs) are preferable results of the prediction, rather than point estimates, because they provide information on the confidence in the prediction. In this paper, two different machine learning approaches to assess PIs of time-series predictions are considered and compared: 1) multilayer perceptron neural networks trained with a multiobjective genetic algorithm and 2) extreme learning machines combined with the nearest neighbors approach. The proposed approaches are applied for short-term wind speed prediction from a real data set of hourly wind speed measurements for the region of Regina in Saskatchewan, Canada. Both approaches demonstrate good prediction precision and provide complementary advantages with respect to different evaluation criteria.