The process of training feedforward neural networks (FFNNs) can benefit from an automated process where the best heuristic to train the network is sought out automatically by means of a highlevel probabilistic-based heuristic.This research introduces a novel population-based Bayesian hyper-heuristic (BHH) that is used to train feedforward neural networks (FFNNs).The performance of the BHH is compared to that of ten popular low-level heuristics, each with different search behaviours.The chosen heuristic pool consists of classic gradient-based heuristics as well as metaheuristics (MHs).The empirical process is executed on fourteen datasets consisting of classification and regression problems with varying characteristics.The BHH is shown to be able to train FFNNs well and provide an automated method for finding the best heuristic to train the FFNNs at various stages of the training process.

The self-organizing feature map (SOM) is an unsupervised neural network. It preserves a high-dimensional training data space's approximate characteristics, while scaling it to a two-dimensional grid. Few SOM-based rule extraction methods exist, and little analysis has been done on their overall viability. This paper presents the novel HybridSOMframework, which allows the combination of a SOM with any standard rule extraction algorithm, creating a customized hybrid rule extractor. Some HybridSOMvariations and traditional rule extraction algorithms are empirically compared, and the framework is critically discussed. This analysis also points to new conclusions on the viability of SOM-based rule extraction, in general.