Skip to main content

armando blanco

Universidad Pedagogica Nacional, Química, Department Member

Followers

10

Following

1

Public Views

University of Granada

Jose Luis Verdegay

University of Granada

Jose Luis Verdegay

University of Granada

Universidad de Murcia

Natalio Krasnogor

Newcastle University

University of Catania

Interests

Uploads

Papers by armando blanco

Applying a fuzzy sets-based heuristic to the protein structure prediction problem

International Journal of Intelligent Systems, 2002

The interface between combinatorial optimization and fuzzy sets-based methodologies is the subjec... more The interface between combinatorial optimization and fuzzy sets-based methodologies is the subject of very active and increasing research. In this context we describe FANS, a fuzzy adaptive neighborhood search optimization heuristic that uses a fuzzy valuation to qualify solutions and adapts its behavior as a function of the search state. FANS may also be regarded as a local search framework.

Learning about FANS behaviour: Knapsack problems as a test case

The Fuzzy Adaptive Neighborhood Search (FANS) method was previously presented and succesfully com... more The Fuzzy Adaptive Neighborhood Search (FANS) method was previously presented and succesfully compared against a genetic algorithm and simulated annealing doing minimization of functions in Rn. Here we propose to evaluate FANS on instances of knapsack with multiple restrictions problems, making comparison against the cited algorithms in order to gain knowledge about the behaviour of our method.

A fuzzy adaptive neighborhood search for function optimization

A Fuzzy Valuation-Based Local Search Framework for Combinatorial Problems

Fuzzy Optimization and Decision Making, 2002

A novel local search method is presented. One of the new elements of this Fuzzy Adaptive Neighbor... more A novel local search method is presented. One of the new elements of this Fuzzy Adaptive Neighborhood Search (FANS) algorithm is a fuzzy valuation, which is used to measure the degree to which the solutions that are considered at the decision stages accomplish a certain qualitative property. FANS is analyzed from two perspectives: first, it is shown how FANS may be adapted to behave like other traditional local search techniques by means of suitable definitions for the fuzzy valuation component. Second, comparisons are made to show the potential of the method as a general purpose optimization tool, when none or minimal knowledge of the problem being solved is available. Both aspects make FANS a valuable tool regarding further developments within the context of decision support systems involving heuristic algorithms.

FANS: A fuzzy adaptive neighborhood search method for optimization problems

Inteligencia Artificial,revista Iberoamericana De Inteligencia Artificial, 2003

The mix between basic ideas from the Fuzzy Set and Systems area with simple optimization methods ... more

Fuzzy automaton induction using neural network

International Journal of Approximate Reasoning, 2001

It has been shown that neural networks are able to infer regular crisp grammars from positive and... more It has been shown that neural networks are able to infer regular crisp grammars from positive and negative examples. The fuzzy grammatical inference (FGI) problem however has received considerably less attention. In this paper we show that a suitable two-layer neural network model is able to infer fuzzy regular grammars from a set of fuzzy examples belonging to a fuzzy language. Once the network has been trained, we develop methods to extract a deterministic representation of the fuzzy automaton encoded in the network that recognizes the training set. Ó

Extracting rules from a (fuzzy/crisp) recurrent neural network using a self-organizing map

International Journal of Intelligent Systems, 2000

ABSTRACT Although the extraction of symbolic knowledge from trained feedforward neural networks h... more ABSTRACT Although the extraction of symbolic knowledge from trained feedforward neural networks has been widely studied, research in recurrent neural networks (RNN) has been more neglected, even though it performs better in areas such as control, speech recognition, time series prediction, etc. Nowadays, a subject of particular interest is (crisp/fuzzy) grammatical inference, in which the application of these neural networks has proven to be suitable. In this paper, we present a method using a self-organizing map (SOM) for extracting knowledge from a recurrent neural network able to infer a (crisp/fuzzy) regular language. Identification of this language is done only from a (crisp/fuzzy) example set of the language. © 2000 John Wiley &amp; Sons, Inc.

Improved fuzzy neural networks for solving relational equations

Fuzzy Sets and Systems, 1995

We present a study on the identification of the systems of fuzzy relational equations based on th... more We present a study on the identification of the systems of fuzzy relational equations based on the identification of fuzzy systems by means of max-min neural networks. Concretely two methods are developed which combined more efficiently two previous ones: Sayto and Mukaidono&amp;#x27;s method and the so-called smoothed derivative technique, already developed by us.

Identification of fuzzy dynamic systems using Max-Min recurrent neural networks

Fuzzy Sets and Systems, 2001

We present a new model of a Max-Min recurrent neural network that is able to identify fuzzy dynam... more

A learning procedure to identify weighted rules by neural networks

Fuzzy Sets and Systems, 1995

In many cases the identification of systems by means of fuzzy rules is given by taking these rule... more In many cases the identification of systems by means of fuzzy rules is given by taking these rules from a predetermined set of possible ones. In this case, the correct description of the system is to be given by a finite set of rules each with an associated weight which assesses its correctness or accuracy. Here we present a method to learn this consistence level or weight by a neural network. The design of this neural network as well as the features of the training models are discussed. The paper concludes with an example.

Constructing linguistic versions for the multicriteria decision support systems preference ranking organization method for enrichment evaluation I and II

International Journal of Intelligent Systems, 2003

The environmental impact assessment (EIA) is a real problem of multicriteria decision making (MCD... more The environmental impact assessment (EIA) is a real problem of multicriteria decision making (MCDM) where information, as much quantitative as qualitative, coexists. The traditional methods of MCDM developed for the EIA discriminates in favor of quantitative information at the expense of qualitative information, because we are unable to integrate this latter information inside their procedure. In this study, we present two new multicriteria decision fuzzy methods called fuzzy in preference ranking organization method for enrichment evaluation (FPROMETHEE2T) I and II, which are able to integrate inside their procedure quantiative and qualitative information. This has been performed by applying a new linguistic representation model based on two tuples. These methods, although they have been developed for EIA problems, can be applied to all sorts of decision-making problems, with information of any nature. Therefore, the application of this method to real problems will lead to better results in MCDM. The main interest of our investigation group currently is to develop a set of different multicriteria decision fuzzy methods to be integrated inside a software program that works as a multicriteria decision aid. © 2003 Wiley Periodicals, Inc.

Extracting Rules from a Fuzzy / Crisp Recurrent Neural Network using a Self-Organizing Map

International Journal of Intelligent Systems

ABSTRACT Although the extraction of symbolic knowledge from trained feedforward neural networks h... more ABSTRACT Although the extraction of symbolic knowledge from trained feedforward neural networks has been widely studied, research in recurrent neural networks (RNN) has been more neglected, even though it performs better in areas such as control, speech recognition, time series prediction, etc. Nowadays, a subject of particular interest is (crisp/fuzzy) grammatical inference, in which the application of these neural networks has proven to be suitable. In this paper, we present a method using a self-organizing map (SOM) for extracting knowledge from a recurrent neural network able to infer a (crisp/fuzzy) regular language. Identification of this language is done only from a (crisp/fuzzy) example set of the language. © 2000 John Wiley &amp; Sons, Inc.

Solving fuzzy relational equations by max-min neural networks

The problem of identifying a fuzzy system has been faced from several points of view which includ... more The problem of identifying a fuzzy system has been faced from several points of view which include statistical methods, neural networks and relational equation-solving approaches. In this paper, we present the use of a neural network without any activation function in order to identify a fuzzy system through the solution of a fuzzy relational equation from a set of examples. The main contribution of this work is to define a “smooth derivative” to be used in the minimization of the energy function which drives the learning procedure. Some examples show the effectiveness of this new approach

A real-coded genetic algorithm for training recurrent neural networks

Neural Networks, 2001

The use of Recurrent Neural Networks is not as extensive as Feedforward Neural Networks. Training... more The use of Recurrent Neural Networks is not as extensive as Feedforward Neural Networks. Training algorithms for Recurrent Neural Networks, based on the error gradient, are very unstable in their search for a minimum and require much computational time when the number of neurons is high. The problems surrounding the application of these methods have driven us to develop new training tools.

Fuzzy automaton induction using neural network

International Journal of Approximate Reasoning, 2001

It has been shown that neural networks are able to infer regular crisp grammars from positive and... more It has been shown that neural networks are able to infer regular crisp grammars from positive and negative examples. The fuzzy grammatical inference (FGI) problem however has received considerably less attention. In this paper we show that a suitable two-layer neural network model is able to infer fuzzy regular grammars from a set of fuzzy examples belonging to a fuzzy language. Once the network has been trained, we develop methods to extract a deterministic representation of the fuzzy automaton encoded in the network that recognizes the training set. Ó

A method to induce fuzzy automata using neural networks

It has been shown that neural networks are able to infer regular crisp grammars from positive and... more It has been shown that neural networks are able to infer regular crisp grammars from positive and negative examples. The fuzzy grammatical inference problem however has received considerably less attention. In this paper we show that a suitable two-layer neural network model is able to infer fuzzy regular grammars from a set of fuzzy examples belonging to a fuzzy language.

Extracting rules from a (fuzzy/crisp) recurrent neural network using a self-organizing map

International Journal of Intelligent Systems, 2000

ABSTRACT Although the extraction of symbolic knowledge from trained feedforward neural networks h... more ABSTRACT Although the extraction of symbolic knowledge from trained feedforward neural networks has been widely studied, research in recurrent neural networks (RNN) has been more neglected, even though it performs better in areas such as control, speech recognition, time series prediction, etc. Nowadays, a subject of particular interest is (crisp/fuzzy) grammatical inference, in which the application of these neural networks has proven to be suitable. In this paper, we present a method using a self-organizing map (SOM) for extracting knowledge from a recurrent neural network able to infer a (crisp/fuzzy) regular language. Identification of this language is done only from a (crisp/fuzzy) example set of the language. © 2000 John Wiley &amp; Sons, Inc.

Identification of fuzzy relational equations by fuzzy neural networks

Fuzzy Sets and Systems, 1995

... will denote by II P cy II-In turn, we can apply any implication function to assess ... [12] S... more

Improved fuzzy neural networks for solving relational equations

Fuzzy Sets and Systems, 1995

We present a study on the identification of the systems of fuzzy relational equations based on th... more We present a study on the identification of the systems of fuzzy relational equations based on the identification of fuzzy systems by means of max-min neural networks. Concretely two methods are developed which combined more efficiently two previous ones: Sayto and Mukaidono&amp;#x27;s method and the so-called smoothed derivative technique, already developed by us.

A genetic algorithm to obtain the optimal recurrent neural network

International Journal of Approximate Reasoning, 2000

Selecting the optimal topology of a neural network for a particular application is a dicult task.... more Selecting the optimal topology of a neural network for a particular application is a dicult task. In the case of recurrent neural networks, most methods only induce topologies in which their neurons are fully connected. In this paper, we present a genetic algorithm capable of obtaining not only the optimal topology of a recurrent neural network but also the least number of connections necessary. Finally, this genetic algorithm is applied to a problem of grammatical inference using neural networks, with very good results. Ó

Applying a fuzzy sets-based heuristic to the protein structure prediction problem

International Journal of Intelligent Systems, 2002

The interface between combinatorial optimization and fuzzy sets-based methodologies is the subjec... more The interface between combinatorial optimization and fuzzy sets-based methodologies is the subject of very active and increasing research. In this context we describe FANS, a fuzzy adaptive neighborhood search optimization heuristic that uses a fuzzy valuation to qualify solutions and adapts its behavior as a function of the search state. FANS may also be regarded as a local search framework.

Learning about FANS behaviour: Knapsack problems as a test case

The Fuzzy Adaptive Neighborhood Search (FANS) method was previously presented and succesfully com... more The Fuzzy Adaptive Neighborhood Search (FANS) method was previously presented and succesfully compared against a genetic algorithm and simulated annealing doing minimization of functions in Rn. Here we propose to evaluate FANS on instances of knapsack with multiple restrictions problems, making comparison against the cited algorithms in order to gain knowledge about the behaviour of our method.

A fuzzy adaptive neighborhood search for function optimization

A Fuzzy Valuation-Based Local Search Framework for Combinatorial Problems

Fuzzy Optimization and Decision Making, 2002

A novel local search method is presented. One of the new elements of this Fuzzy Adaptive Neighbor... more A novel local search method is presented. One of the new elements of this Fuzzy Adaptive Neighborhood Search (FANS) algorithm is a fuzzy valuation, which is used to measure the degree to which the solutions that are considered at the decision stages accomplish a certain qualitative property. FANS is analyzed from two perspectives: first, it is shown how FANS may be adapted to behave like other traditional local search techniques by means of suitable definitions for the fuzzy valuation component. Second, comparisons are made to show the potential of the method as a general purpose optimization tool, when none or minimal knowledge of the problem being solved is available. Both aspects make FANS a valuable tool regarding further developments within the context of decision support systems involving heuristic algorithms.

FANS: A fuzzy adaptive neighborhood search method for optimization problems

Inteligencia Artificial,revista Iberoamericana De Inteligencia Artificial, 2003

The mix between basic ideas from the Fuzzy Set and Systems area with simple optimization methods ... more

Fuzzy automaton induction using neural network

International Journal of Approximate Reasoning, 2001

It has been shown that neural networks are able to infer regular crisp grammars from positive and... more It has been shown that neural networks are able to infer regular crisp grammars from positive and negative examples. The fuzzy grammatical inference (FGI) problem however has received considerably less attention. In this paper we show that a suitable two-layer neural network model is able to infer fuzzy regular grammars from a set of fuzzy examples belonging to a fuzzy language. Once the network has been trained, we develop methods to extract a deterministic representation of the fuzzy automaton encoded in the network that recognizes the training set. Ó

Extracting rules from a (fuzzy/crisp) recurrent neural network using a self-organizing map

International Journal of Intelligent Systems, 2000

ABSTRACT Although the extraction of symbolic knowledge from trained feedforward neural networks h... more ABSTRACT Although the extraction of symbolic knowledge from trained feedforward neural networks has been widely studied, research in recurrent neural networks (RNN) has been more neglected, even though it performs better in areas such as control, speech recognition, time series prediction, etc. Nowadays, a subject of particular interest is (crisp/fuzzy) grammatical inference, in which the application of these neural networks has proven to be suitable. In this paper, we present a method using a self-organizing map (SOM) for extracting knowledge from a recurrent neural network able to infer a (crisp/fuzzy) regular language. Identification of this language is done only from a (crisp/fuzzy) example set of the language. © 2000 John Wiley &amp; Sons, Inc.

Improved fuzzy neural networks for solving relational equations

Fuzzy Sets and Systems, 1995

We present a study on the identification of the systems of fuzzy relational equations based on th... more We present a study on the identification of the systems of fuzzy relational equations based on the identification of fuzzy systems by means of max-min neural networks. Concretely two methods are developed which combined more efficiently two previous ones: Sayto and Mukaidono&amp;#x27;s method and the so-called smoothed derivative technique, already developed by us.

Identification of fuzzy dynamic systems using Max-Min recurrent neural networks

Fuzzy Sets and Systems, 2001

We present a new model of a Max-Min recurrent neural network that is able to identify fuzzy dynam... more

A learning procedure to identify weighted rules by neural networks

Fuzzy Sets and Systems, 1995

In many cases the identification of systems by means of fuzzy rules is given by taking these rule... more In many cases the identification of systems by means of fuzzy rules is given by taking these rules from a predetermined set of possible ones. In this case, the correct description of the system is to be given by a finite set of rules each with an associated weight which assesses its correctness or accuracy. Here we present a method to learn this consistence level or weight by a neural network. The design of this neural network as well as the features of the training models are discussed. The paper concludes with an example.

Constructing linguistic versions for the multicriteria decision support systems preference ranking organization method for enrichment evaluation I and II

International Journal of Intelligent Systems, 2003

The environmental impact assessment (EIA) is a real problem of multicriteria decision making (MCD... more The environmental impact assessment (EIA) is a real problem of multicriteria decision making (MCDM) where information, as much quantitative as qualitative, coexists. The traditional methods of MCDM developed for the EIA discriminates in favor of quantitative information at the expense of qualitative information, because we are unable to integrate this latter information inside their procedure. In this study, we present two new multicriteria decision fuzzy methods called fuzzy in preference ranking organization method for enrichment evaluation (FPROMETHEE2T) I and II, which are able to integrate inside their procedure quantiative and qualitative information. This has been performed by applying a new linguistic representation model based on two tuples. These methods, although they have been developed for EIA problems, can be applied to all sorts of decision-making problems, with information of any nature. Therefore, the application of this method to real problems will lead to better results in MCDM. The main interest of our investigation group currently is to develop a set of different multicriteria decision fuzzy methods to be integrated inside a software program that works as a multicriteria decision aid. © 2003 Wiley Periodicals, Inc.

Extracting Rules from a Fuzzy / Crisp Recurrent Neural Network using a Self-Organizing Map

International Journal of Intelligent Systems

ABSTRACT Although the extraction of symbolic knowledge from trained feedforward neural networks h... more ABSTRACT Although the extraction of symbolic knowledge from trained feedforward neural networks has been widely studied, research in recurrent neural networks (RNN) has been more neglected, even though it performs better in areas such as control, speech recognition, time series prediction, etc. Nowadays, a subject of particular interest is (crisp/fuzzy) grammatical inference, in which the application of these neural networks has proven to be suitable. In this paper, we present a method using a self-organizing map (SOM) for extracting knowledge from a recurrent neural network able to infer a (crisp/fuzzy) regular language. Identification of this language is done only from a (crisp/fuzzy) example set of the language. © 2000 John Wiley &amp; Sons, Inc.

Solving fuzzy relational equations by max-min neural networks

The problem of identifying a fuzzy system has been faced from several points of view which includ... more The problem of identifying a fuzzy system has been faced from several points of view which include statistical methods, neural networks and relational equation-solving approaches. In this paper, we present the use of a neural network without any activation function in order to identify a fuzzy system through the solution of a fuzzy relational equation from a set of examples. The main contribution of this work is to define a “smooth derivative” to be used in the minimization of the energy function which drives the learning procedure. Some examples show the effectiveness of this new approach

A real-coded genetic algorithm for training recurrent neural networks

Neural Networks, 2001

The use of Recurrent Neural Networks is not as extensive as Feedforward Neural Networks. Training... more The use of Recurrent Neural Networks is not as extensive as Feedforward Neural Networks. Training algorithms for Recurrent Neural Networks, based on the error gradient, are very unstable in their search for a minimum and require much computational time when the number of neurons is high. The problems surrounding the application of these methods have driven us to develop new training tools.

Fuzzy automaton induction using neural network

International Journal of Approximate Reasoning, 2001

It has been shown that neural networks are able to infer regular crisp grammars from positive and... more It has been shown that neural networks are able to infer regular crisp grammars from positive and negative examples. The fuzzy grammatical inference (FGI) problem however has received considerably less attention. In this paper we show that a suitable two-layer neural network model is able to infer fuzzy regular grammars from a set of fuzzy examples belonging to a fuzzy language. Once the network has been trained, we develop methods to extract a deterministic representation of the fuzzy automaton encoded in the network that recognizes the training set. Ó

A method to induce fuzzy automata using neural networks

It has been shown that neural networks are able to infer regular crisp grammars from positive and... more It has been shown that neural networks are able to infer regular crisp grammars from positive and negative examples. The fuzzy grammatical inference problem however has received considerably less attention. In this paper we show that a suitable two-layer neural network model is able to infer fuzzy regular grammars from a set of fuzzy examples belonging to a fuzzy language.

Extracting rules from a (fuzzy/crisp) recurrent neural network using a self-organizing map

International Journal of Intelligent Systems, 2000

ABSTRACT Although the extraction of symbolic knowledge from trained feedforward neural networks h... more ABSTRACT Although the extraction of symbolic knowledge from trained feedforward neural networks has been widely studied, research in recurrent neural networks (RNN) has been more neglected, even though it performs better in areas such as control, speech recognition, time series prediction, etc. Nowadays, a subject of particular interest is (crisp/fuzzy) grammatical inference, in which the application of these neural networks has proven to be suitable. In this paper, we present a method using a self-organizing map (SOM) for extracting knowledge from a recurrent neural network able to infer a (crisp/fuzzy) regular language. Identification of this language is done only from a (crisp/fuzzy) example set of the language. © 2000 John Wiley &amp; Sons, Inc.

Identification of fuzzy relational equations by fuzzy neural networks

Fuzzy Sets and Systems, 1995

... will denote by II P cy II-In turn, we can apply any implication function to assess ... [12] S... more

Improved fuzzy neural networks for solving relational equations

Fuzzy Sets and Systems, 1995

We present a study on the identification of the systems of fuzzy relational equations based on th... more We present a study on the identification of the systems of fuzzy relational equations based on the identification of fuzzy systems by means of max-min neural networks. Concretely two methods are developed which combined more efficiently two previous ones: Sayto and Mukaidono&amp;#x27;s method and the so-called smoothed derivative technique, already developed by us.

A genetic algorithm to obtain the optimal recurrent neural network

International Journal of Approximate Reasoning, 2000

Selecting the optimal topology of a neural network for a particular application is a dicult task.... more Selecting the optimal topology of a neural network for a particular application is a dicult task. In the case of recurrent neural networks, most methods only induce topologies in which their neurons are fully connected. In this paper, we present a genetic algorithm capable of obtaining not only the optimal topology of a recurrent neural network but also the least number of connections necessary. Finally, this genetic algorithm is applied to a problem of grammatical inference using neural networks, with very good results. Ó