Soft Computing, Artificial Intelligence and Applications

Gradient Omissive Descentis A Minimization Algorithm Gustavo A. Lado and Enrique C. Segura Universidad de Buenos Aires Cyprus ABSTRACT This article presents a promising new gradient-based backpropagation algorithm for multi-layer feedforward networks. The method requires no manual selection of global hyperparameters and is capable of dynamic local adaptations using only first-order information at a low computational cost. Its semi-stochastic nature makes it fit for mini-batch training and robust to different architecture choices and data distributions. Experimental evidence shows that the proposed algorithm improves training in terms of both convergence rate and speed as compared with other well known techniques. KEYWORDS Neural Networks, Backpropagation, Cost Function Minimization Original Source URL: http://aircconline.com/ijscai/V8N1/8119ijscai03.pdf http://airccse.org/journal/ijscai/current2019.html

Forecasting Macroeconomical Indices with Machine Learning : Impartial Analysis of the Relation Between Economic Freedom and Quality of Life Jonathan Staufer and Patricia Brockmann Technische Hochschule Nurnberg, Germany ABSTRACT The importance of economic freedom has often been stressed by supporters of liberalism, but can its actu-al effect be observed in a data driven, objective way? To analyze this relation the Economic Freedom of the World (EFW) index and the Human Development Index (HDI) were examined with modern machine learning algorithms and a wide-ranging approach. Considering the EFW index’s preference of a liberal-istic oriented economic policy, an objective recommendation for creating an economic policy that im-proves people’s everyday lives might be derived by the analysis results. It was found that these more ad-vanced algorithms achieve a considerably stronger correlation between both indices than pure statistical means yet leave a small room for interpretati...