The goal of this paper is to investigate to what extent a rule learning heuristic can be learned from experience. Our basic approach is to learn a large number of rules and record their performance on the test set. Subsequently, we train regression algorithms on predicting the test set performance from training set characteristics. We investigate several variations of this basic scenario, inclu...

Typically rule extraction is done for the purposes of human interpretation. However, there are other possible applications of rule extraction. One practical application is transfer learning, in which knowledge learned in one task is used to aid in learning a related task. The extracted rules, which explain the learned solution to the first task, can be considered advice on how to approach the s...

The present contribution discusses a Riemannian-gradient-based algorithm and a projection-based learning algorithm over a curved parameter space for single-neuron learning. We consider the ‘blind deconvolution’ signal processing problem. The learning rule naturally arises from a criterion-function minimization over the unitary hyper-sphere setting. We consider the blind deconvolution performanc...

Using the theory of Web Data Mining, this paper proposes a physics discipline personalized learning evaluation system model based on decision tree algorithm. The overall structure of this system model, which is applied to the network-based education, is presented. The key part of the model, data collection module and personalized evaluation module are introduced. The advantages and disadvantage...

Association rule mining has recently become a popular area of research. The most expensive step of discovering association rules is to find so-called frequent item sets. The focus of this paper is efficient mining of frequent item sets when the input data contains categorical and quantitative attributes. We propose a new Apriori-like algorithm to solve this problem. The new algorithm, that we h...

The direction set by Wilson’s XCS is that modern Learning Classifier Systems can be characterized by their use of rule accuracy as the utility metric for the search algorithm(s) discovering useful rules. Such searching typically takes place within the restricted space of coactive rules for efficiency. This paper gives an overview of the evolution of Learning Classifier Systems up to XCS, and th...

We present a general and systematic method for neural network design based on the genetic algorithm. The technique works in conjunction with network learning rules, addressing aspects of the network's gross architecture, connectivity, and learning rule parameters. Networks can be optimiled for various applicationspecific criteria, such as learning speed, generalilation, robustness and connectiv...

This paper presents a novel induction algorithm, Rulearner, which induces classification rules using a Galois lattice as an explicit map through the search space of rules. The Rulearner system is shown to compare favorably with commonly used symbolic learning methods which use heuristics rather than an explicit map to guide their search through the rule space. Furthermore, our learning system i...

Association rule mining is considered as a Major technique in data mining applications. It reveals all interesting relationships, called associations, in a potentially large database. However, how interesting a rule is depends on the problem a user wants to solve. Existing approaches employ different parameters to guide the search for interesting rules. Class association rules which combine ass...

Methods for learning decision rules are being successfully applied to many problem domains, in particular when understanding and interpretation of the learned model is necessary. In many real life problems, we would like to predict multiple related (nominal or numeric) target attributes simultaneously. While several methods for learning rules that predict multiple targets at once exist, they ar...