In this article, we focus on the opacity issue of sub-symbolic machine learning predictors by
promoting two complementary activities—symbolic knowledge extraction (SKE) and …

It is becoming increasingly apparent that, without some form of explanation capability, the
full potential of trained artificial neural networks (ANNs) may not be realised. This survey …

This research project investigates the ability of neural networks, specifically, the
backpropagation algorithm, to integrate fundamental and technical analysis for financial …

The growing self-organizing map (GSOM) algorithm is presented in detail and the effect of a
spread factor, which can be used to measure and control the spread of the GSOM, is …

To date, the preponderance of techniques for eliciting the knowledge embedded in trained
artificial neural networks (ANN's) has focused primarily on extracting rule-based …

A new methodology of extraction, optimization, and application of sets of logical rules is
described. Neural networks are used for initial rule extraction, local or global minimization …

In many applications, black-box prediction is not satisfactory, and understanding the data is
of critical importance. Typically, approaches useful for understanding of data involve logical …

Neural networks (NNs) have been successfully applied to solve a variety of application
problems including classification and function approximation. They are especially useful as …

Before symbolic rules are extracted from a trained neural network, the network is usually
pruned so as to obtain more concise rules. Typical pruning algorithms require retraining the …

Data mining, which is also referred to as knowledge discovery in databases, is the process
of extracting valid, previously unknown, comprehensible and actionable information from …