G. M. Sacha

M. Konomi, G. M. Sacha

A method that allows us to give a different treatment to any neuron inside feedforward neural networks is presented. The algorithm has been implemented with two very different learning methods: a standard Back-propagation (BP) procedure and an evolutionary algorithm. First, we have demonstrated that the EA training method converges faster and gives more accurate results than BP. Then we have made a full analysis of the effects of turning off different combinations of neurons after the training phase. We demonstrate that EA is much more robust than BP for all the cases under study. Even in the case when two hidden neurons are lost, EA training is still able to give good average results. This difference implies that we must be very careful when pruning or redundancy effects are being studied since the network performance when losing neurons strongly depends on the training method. Moreover, the influence of the individual inputs will also depend on the training algorithm. Since EA keeps a good classification performance when units are lost, this method could be a good way to simulate biological learning systems since they must be robust against deficient neuron performance. Although biological systems are much more complex than the simulations shown in this article, we propose that a smart training strategy such as the one shown here could be considered as a first protection against the losing of a certain number of neurons.

P. Molins-Ruano, C. González-Sacristán, F. Díez et al.

In this work, we show a methodology aimed to improve the quality of the assessment process for subjects related to basic programming. The method takes into account the relevance of the items and the students answers to follow different paths to improve the accuracy of the assessment process. We have developed numerical simulations and experiments with real students that demonstrate the advantages of this model when compared with traditional evaluation tools. This method improves the objectiveness and takes into account the relevance of the subject contents. We also demonstrate that the architecture of the algorithm is fully compatible with traditional multiple choice test formalisms. Our results can be directly used in computer-assisted tests for different subjects and disciplines, as well as used by the students as a self-evaluation tool with the objective of correcting their deficiencies in the learning process.