David Hidalgo García

Magnetization reversal asymmetry in Fe/MgO(0 0 1) thin films

We study the in-plane magnetization process in 200 A Fe(0 0 1) thin films grown by sputtering at normal incidence. In spite of this growth geometry, a small uniaxial in plane magnetic anisotropy, whose origin is not totally understood, is found superimposed to the expected cubic biaxial one. This has a dramatic effect both on the reversal process and the domain structure. A combined longitudinal and transversal Kerr study shows the different switching processes (180° walls along the main easy axis versus 90° along the secondary easy axis) depending on the relative orientation of the magnetic field with respect to the Fe crystallographic axes. Remarkably, this two- and sometimes three-step switching process appears only when the field is applied along certain crystallographic directions. These findings are corroborated by domain observations.

Overview of the SLAVE learning algorithm: A review of its evolution and prospects

AbstractInductive learning has been—and still is—one of the most important methods that can be applied in classification problems. Knowledge is usually represented using rules that establish relationships between the problem variables. SLAVE (Structural Learning Algorithm in a Vague Environment) was one of the first fuzzy-rule learning algorithms, and since its first implementation in 1994 it has been frequently used to benchmark new algorithms. Over time, the algorithm has undergone several modifications, and identifying the different versions developed is not an easy task. In this work we present a study of the evolution of the SLAVE algorithm from 1996 to date, marking the most important landmarks as definitive versions. In order to add these final versions to the KEEL platform, Java implementations have been developed. Finally, we describe the parameters used and the results obtained in the experimental study.

A feature construction approach for genetic iterative rule learning algorithm

This paper presents a proposal that introduces the use of feature construction in a fuzzy rule learning algorithm. This is done by means of the combination of two different approaches together with a new learning strategy. The first of these two approaches consists of using relations in the antecedent of fuzzy rules while the second one employs functions in the antecedent of that rules. Thus, the method we propose tries to integrate these two models so that, using a learning strategy that allows us to start learning more general rules and finish the process learning more specific ones, we are able to increase the amount of information extracted from the initial variables. The experimental results show that the proposed method obtains a good trade-off among accuracy, interpretability and time needed to get the model in relation to the rest of algorithms using feature construction involved in the comparison.

An interpretability improvement for fuzzy rule bases obtained by the iterative rule learning approach

Interpretability is one of the key concepts in many of the applications using the fuzzy rule-based approach. It is well known that there are many different criteria around this concept, the complexity being one of them. In this paper, we focus our efforts in reducing the complexity of the fuzzy rule sets. One of the most interesting approaches for learning fuzzy rules is the iterative rule learning approach. It is mainly characterized by obtaining rules covering few examples in final stages, being in most cases useless to represent the knowledge. This behavior is due to the specificity of the extracted rules, which eventually creates more complex set of rules. Thus, we propose a modified version of the iterative rule learning algorithm in order to extract simple rules relaxing this natural trend. The main idea is to change the rule extraction process to be able to obtain more general rules, using pruned searching spaces together with a knowledge simplification scheme able to replace learned rules. The experimental results prove that this purpose is achieved. The new proposal reduces the complexity at both, the rule and rule base levels, maintaining the accuracy regarding to previous versions of the algorithm.

A new iterative model to simplify the knowledge extracted on a fuzzy rule-based learning algorithm

Different fuzzy rule-based learning algorithms use the sequential covering strategy. This model applies a problem decomposition strategy, in which the task of finding a complete rule base is reduced to a sequence of subproblems in each of which the solution is to add a single rule. Now, we are interested in introducing additional capabilities in this strategy in order to review the knowledge previously extracted. Thus, our main objective is that in each iteration instead of only being able to add rules, we can propose three different options: to add the best rule that increases the prediction capability of the rule base, to add the best rule that replaces one or more rules previously learned without loosing accuracy or do not add any rule, if the rule base can not be improved. The experimental results show that this proposal maintains the accuracy of the model as well as the average number of rules but significantly reducing the number of conditions per database, which means that rules are more general. Therefore, this new iterative scheme improves the interpretability of the model obtained.

An empirical study about the behavior of a genetic learning algorithm on searching spaces pruned by a completeness condition

The main difficulty faced by a learning algorithm is to find the appropriate knowledge inside of the huge search space of possible solutions. Typically, the researchers try to solve this problem developing more efficient search algorithms, defining “ad-hoc” heuristic for the specific problem or reducing the expressiveness of the knowledge representation. This work explores an alternative way that consists of reducing the search space using a completeness condition. The proposed model is implemented on NSLV, a fuzzy rule learning algorithm based on genetic algorithms. We present an experimental study of the behavior of NSLV on pruned search spaces. The experimental results show that when we work with these spaces it is possible to find a good trace-off among prediction capacity, complexity of the knowledge obtained and learning time.

A FILTER PROPOSAL FOR INCLUDING FEATURE CONSTRUCTION IN A GENETIC LEARNING ALGORITHM

In system identification process often a predetermined set of features is used. However, in many cases it is difficult to know a priori whether the selected features were really the more appropriate ones. This is the reason why the feature construction techniques have been very interesting in many applications. Thus, the current proposal introduces the use of these techniques in order to improve the description of fuzzy rule-based systems. In particular, the idea is to include feature construction in a genetic learning algorithm. The construction of attributes in this study will be restricted to the inclusion of functions defined on the initial attributes of the system. Since the number of functions and the number of attributes can be very large, a filter model, based on the use of information measures, is introduced. In this way, the genetic algorithm only needs to explore the particular new features that may be of greater interest to the final identification of the system. In order to manage the knowledge provided by the new attributes based on the use of functions we propose a new model of rule by extending a basic learning fuzzy rule-based model. Finally, we show the experimental study associated with this work.

A two-step approach of feature construction for a genetic learning algorithm

Traditionally, fuzzy rule based models work with a fixed set of features to describe a particular problem. Our proposal is to use feature construction by means of functions in order to obtain new variables that allow us to get more information about the problem. In particular, we propose the use of previously defined functions over the input variables in the antecedent of the rules. This let us to know if a combination of variables is able to provide us with more information than each one of them separately. In addition, we use a structure that helps us to manage and also restrict the number of functions under consideration by the learning algorithm. We also present a new model of rule in order to represent this kind of knowledge by extending a basic learning fuzzy rule-based model. Finally, we show the experimental study associated with this work.

On the use of an incremental approach to learn fuzzy classification rules for big data problems

The MapReduce paradigm is a programming model mainly thought to process big data sets. This model has recently been used in a new proposal of a linguistic fuzzy rule-based learning algorithm. One of the most important aspects of this proposal is the use of a parallel and distributed algorithm. An alternative to this parallel and distributed organization is the use of an incremental learning algorithm in a sequential schema. We propose an incremental algorithm to learn fuzzy classification rules based on this idea and we also demonstrate through the experimental study that the proposal is very competitive when it is applied to big data problems.

Using a sequential covering strategy for discovering fuzzy rules incrementally

The sequential covering strategy has been and still is a very common way to develop rule learning algorithms. This strategy follows a greedy procedure to learn rules, where, after each step one rule is obtained. Recently, we proposed a new sequential covering strategy that allowed the review of previously learned knowledge during the learning process itself. This review of knowledge allowed the algorithm to adapt to changes that may occur in the context of learning. Specifically, in this paper we consider the changes produced by the addition of new training examples, and therefore we make a proposal of incremental learning of fuzzy rules. We have performed several experiments to test the behavior of the proposal and the results have been very promising.