Search

An extension to Hopfield's model of associative memory is studied in the present work. In particular, this paper is focused in giving solutions to the two main problems present in the model: the apparition of spurious patterns in the learning phase (implying the well-known and undesirable effect of storing the opposite pattern) and the problem of its reduced capacity (the probability of error in the retrieving phase increases as the number of stored patterns grows). In this work, a method to avoid spurious patterns is presented and studied, and an explanation to the previously mentioned effect is given. Another novel technique to increase the capacity of a network is proposed here, based on the idea of using several reference points when storing patterns. It is studied in depth, and an explicit formula for the capacity of the network is provided. This formula shows the linear dependence of the capacity of the new model on the number of reference points, implying the increase of the capacity in this model. [ABSTRACT FROM AUTHOR]

We describe a new software tool, called Spieldose (in English, musical box), suited to the automatic music composition task. Our system is based on the paradigm of Interactive Genetic Algorithms (abbreviated as Interactive GA) where the parent selection stage in a typical GA is made by the user according to his/her subjective criteria. The tool permits to integrate the interaction between the system and the potential users when they create their melodies. One important contribution of this work is the proposal of specific musical genetic operators (different types of crossover, mutation and improvement operators) which ensure that the generated melodies are in concordance with Music Theory and they are also nice to listening. Moreover, our software tool can be customized to a particular musical style by including the specific musical knowledge domain in the system. For validation purposes, we used Spieldose to compose different pieces corresponding to the classicism. [ABSTRACT FROM AUTHOR]

Cardiac auscultation still remains today as the basic technique to easily achieve a cardiac valvular diagnosis. Nowadays, auscultation can be powered with automated computer-aided analysis systems to provide objective, accurate, documented and cost-effective diagnosis. This is particulary useful when such systems offer remote diagnosis capabilities. ASEPTIC is a telediagnosis system for cardiac sounds that allows the analysis of remote phonocardiographic signals. The pattern recognition stage of ASEPTIC is presented in this paper. It is based in feature selection from the cardiac events, and classification using a multilayer perceptron artificial neural network trained with Levenberg-Marquardt algorithm for fast convergence. Three categories of records have been considered: normal, with holosystolic murmur, and with midsystolic murmur. Experimental results show high correct classification rates for the three categories: 100%, 92.69%, and 97.57%, respectively. [ABSTRACT FROM AUTHOR]

In this paper we propose a method for building possibilistic temporal constraint networks that better summarizes the huge set of mined timed-stamped sequences from a temporal data mining process. It belongs to the well-known second-order data mining problem, where the vast amount of simple sequences or patterns needs to be summarized further. It is a very important topic because the huge number of temporal associations extracted in the temporal data mining step makes the knowledge discovery process practically unmanageable for human experts. The method is based on the Theory of Evidence of Shafer as a mathematical tool for obtaining the fuzzy measures involved in the temporal network. This work also presents briefly a practical example describing an application of this proposal in the Intensive Care domain. [ABSTRACT FROM AUTHOR]

Temporal abstraction methods produce high level descriptions of a parameter evolution from collections of temporal data. As the level of abstraction of the data is increased, it becomes easier to use them in a reasoning process based on high-level explicit knowledge. Furthermore, the volume of data to be treated is reduced and, subsequently, the reasoning becomes more efficient. Besides, there exist domains, such as medicine, in which there is some imprecision when describing the temporal location of data, especially when they are based on subjective observations. In this work, we describe how the use of fuzzy temporal constraint networks enables temporal imprecision to be considered in temporal abstraction. [ABSTRACT FROM AUTHOR]

Conductive plastics have become an alternative to traditional metallic cabinets to shield boxes from electromagnetic interferences. The wide range of available conductivities with these materials can satisfy any particular design. A design with an outer metallic layer and an inner layer of conductive dielectric can obtain advantages from both materials. In this paper the design by means of genetic algorithms of electronic systems cabinets made of new plastic materials to reduce electromagnetic radiated interferences in enclosures with an aperture is described. This optimization procedure requires the use of electromagnetic simulators with a high computational cost. A 2D simulation tool is used in this work for evaluating 3D structures, reducing drastically the computation time. The relationship between obtained solutions and skin depth parameter is evaluated to help in design procedures. A commercial 3D full wave electromagnetic tool has been used to validate the obtained results. [ABSTRACT FROM AUTHOR]

In this paper we present a software tool for the automatic design of collective behaviors in animated feature films. The most successful existing commercial solutions used in animation studios require an explicit knowledge by the designer of the AI or other techniques and involve the hand design of many parameters. Our main motivation consists in developing a design tool that permits creating the behaviors of the characters from a high level perspective, using general concepts related to the final desired objectives, and to judge these behaviors from a visual point of view, thus abstracting the designer from the computational techniques in the system core. In this case, a bioinspired approach has been followed consisting in the incremental generation of controllers for simulated agents using evolution. An example of flocking activity is created with the system. [ABSTRACT FROM AUTHOR]

Multiobjective optimization problems have become an important issue at many engineering problems. A tradeoff between several design criteria is required and important efforts are made for the development of Multiobjective Optimization Techniques and, in particular, Evolutionary Multiobjective Optimization. Usually these algorithms produce a set of optimum solutions in Pareto sense, there is not a unique solution. The designer (Decision Maker) has to finally select one solution for each particular problem, then he has to select from a set of Pareto solutions, the most adequate solution according to his preferences. It is widely accepted that visualization tools are valuable tools to provide the Decision Maker (DM) with a meaningful way to analyze Pareto set and then to help to select an adequate solution. This work describes a new graphical way to represent high dimensional and large sets of Pareto solutions, allowing an easier analysis, and helping the DM to select an adequate solution. [ABSTRACT FROM AUTHOR]

One of the most important feature of the Neural Gas is its ability to preserve the topology in the projection of highly dimensional input spaces to lower dimensions vector quantizations. For this reason, the Neural Gas has proven to be a valuable tool in data mining applications. In this paper an incremental ensemble method for the combination of various Neural Gas models is proposed. Several models are trained with bootstrap samples of the data, the "codebooks" with similar Voronoi polygons are merged in one fused node and neighborhood relations are established by linking similar fused nodes. The aim of combining the Neural Gas is to improve the quality and robustness of the topological representation of the single model. We have called this model Fusion-NG. Computational experiments show that the Fusion-NG model effectively preserves the topology of the input space and improves the representation of the single Neural Gas model. Furthermore, the Fusion-NG explicitly shows the neighborhood relations of it prototypes. We report the performance results using synthetic and real datasets, the latter obtained from a benchmark site. [ABSTRACT FROM AUTHOR]

In this paper, we confront a variant of the cutting-stock problem with multiple objectives. The starting point is a solution calculated by a heuristic algorithm, termed SHRP, that aims to optimize the two main objectives, i.e. the number of cuts and the number of different patterns. Here, we propose a multi-objective genetic algorithm to optimize other secondary objectives such as changeovers, completion times of orders pondered by priorities and open stacks. We report experimental results showing that the multi-objective genetic algorithm is able to improve the solutions obtained by SHRP on the secondary objectives. [ABSTRACT FROM AUTHOR]

In this paper we propose a hybrid method, combining heuristics and local search, to solve flow shop scheduling problems under uncertainty. This method is compared with a genetic algorithm from the literature, enhanced with three new multi-objective functions. Both single objective and multi-objective approaches are taken for two optimisation goals: minimisation of completion time and fulfilment of due date constraints. We present results for newly generated examples that illustrate the effectiveness of each method. [ABSTRACT FROM AUTHOR]

We consider the fuzzy job shop problem, a job shop scheduling problem with uncertain task durations and flexible due dates, with different objective functions and a GA as solving method. We propose a method to generate benchmark problems with variable uncertainty and analyse the performance of the objective functions in terms of the objective values and the sensitivity to variations in the uncertainty. [ABSTRACT FROM AUTHOR]

Auscultation of the heart is a medical technique that still today is used to provide a fast diagnosis about the heart condition. Compression of the heart sounds (or phonocardiogram) is very convenient to reduce bandwidth in telediagnosis systems that aid the physician in the evaluation of the cardiovascular state. The compression algorithm used depends on several parameters, which can take a diversity of values. Genetic algorithms have been used to obtain the optimal set of values for the compression parameters that optimize the performance of the compression for a test set of cardiac recordings. The optimized results were obtained very quickly, and optimal values agreed for (almost) all the test records. [ABSTRACT FROM AUTHOR]

The article presents an integrated resolution of the joint production and maintenance scheduling problem in hybrid flowshop. Two resolution methods are used on the basis of a new coding to represent a joint production and maintenance scheduling: Taboo search where we proposed an algorithm for the generation of a joint initial solution and neighbourhood, and GA where we proposed new joint operators for crossover and mutation. Computational experiments are conducted on a large set of instances and the resulting genetic algorithm gives the best results so far. [ABSTRACT FROM AUTHOR]

This work presents the results on applying a genetic approach for solving the Dial-A-Ride Problem (DARP). The problem consists of assigning and scheduling a set of user transport requests to a fleet of available vehicles in the most efficient way according to a given objective function. The literature offers different heuristics for solving DARP, a well known NP-hard problem, which range from traditional insertion and clustering algorithms to soft computing techniques. On the other hand, the approach through Genetic Algorithms (GA) has been experienced in problems of combinatorial optimization. We present our experience and results of a study to develop and test different GAs in the aim of finding an appropriate encoding and configuration, specifically for the DARP problem with time windows. [ABSTRACT FROM AUTHOR]

The new learning classifier system is described to classify real-valued data. The approach applies the continous-valued context-free grammar based system GCS. In order to handle effectively, the terminal rules have been replaced by the so-called environment probing rules. The rGCS model has been tested on the checkerboard problem. [ABSTRACT FROM AUTHOR]

In this work we use simulated evolution to corroborate the adaptability of the natural genetic code. An adapted genetic algorithm searches for optimal hypothetical codes. The adaptability is measured as the average variation of the hydrophobicity that experiment the encoded amino acids when errors or mutations are presented in the codons of the hypothetical codes. Different types of mutations and base position mutation probabilities are considered in this study. [ABSTRACT FROM AUTHOR]

In this article, a methodology to obtain the Feasible Parameter Set (FPS) and a nominal model in a non-linear robust identification problem is presented. Several norms are taken into account simultaneously to define the FPS which improves the model quality but, as counterpart, it increases the optimization problem complexity. To determine the FPS a multimodal optimization problem with an infinite number of minima, which constitute the FPS, is presented and a special evolutionary algorithm (ε−GA) is used to characterize it. Finally, an application to a thermal process identification, where · ∞  and ·1 norms have been considered simultaneously, is presented to illustrate the technique. [ABSTRACT FROM AUTHOR]

We consider the numerical evolutionary optimization of dynamic molecular alignment by shaped femtosecond laser pulses. We study a simplified model of this quantum control problem, which allows the full physical investigation of the optimal solutions. By using specific variants of Derandomized Evolution Strategies, subject to parameterizations which are known to be superior for this problem, the numerical results reveal different conceptual physics structures for the different optimization procedures. These results are strong both from the algorithmic as well as from the physics perspectives. This shows that Natural Computing techniques can be used to derive new insights into Physics. [ABSTRACT FROM AUTHOR]

The paper describes a methodology for constructing a possible combination of different basis functions (sigmoidal and product) for the hidden layer of a feed forward neural network, where the architecture, weights and node typology are learned based on evolutionary programming. This methodology is tested using simulated Gaussian data set classification problems with different linear correlations between input variables and different variances. It was found that combined basis functions are the more accurate for classification than pure sigmoidal or product-unit models. Combined basis functions present competitive results which are obtained using linear discriminant analysis, the best classification methodology for Gaussian data sets. [ABSTRACT FROM AUTHOR]

This article proposes a context-free grammar to be used in grammar-guided genetic programming systems to automatically design feed-forward neural architectures. This grammar has three important features. The sentences that belong to the grammar are binary strings that directly encode all the valid neural architectures only. This rules out the appearance of illegal points in the search space. Second, the grammar has the property of being ambiguous and semantically redundant. Therefore, there are alternative ways of reaching the optimum. Third, the grammar starts by generating small networks. This way it can efficiently adapt to the complexity of the problem to be solved. From the results, it is clear that these three properties are beneficial to the convergence process of the grammar-guided genetic programming system. [ABSTRACT FROM AUTHOR]

In this work we present a new proposal in order to model the probability distribution in the estimation of distribution algorithms. This approach is based on using dependency networks [1] instead of Bayesian networks or simpler models in which structure is limited. Dependency networks are probabilistic graphical models similar to Bayesian networks, but with a significant difference: they allow directed cycles in the graph. This difference can be an important advantage because of two main reasons. First, in some real problems cyclic relationships appear between variables an this fact cannot be represented in a Bayesian network. Secondly, dependency networks can be built easily due to the fact that there is no need to check the existence of cycles as in a Bayesian network. In this paper we propose to use a general (multivariate) model in order to deal with a richer representation, however, in this initial approach to the problem we also propose to constraint the construction phase in order to use only bivariate statistics. The algorithm is compared with classical approaches with the same complexity order, i.e. bivariate models as chains and trees. [ABSTRACT FROM AUTHOR]

Nature has been a continuous source of inspiration for many successful techniques, algorithms and computational metaphors. We outline such a inspiration here, in the context of bio-inspired congestion control (BICC) algorithms. In this paper a realistic predator-prey model is mapped to the Internet congestion control mechanism. This mapping leads to a bio-inspired congestion control scheme. Dynamic and equilibrium properties of developed algorithm are good enough according to the simulation results. [ABSTRACT FROM AUTHOR]

Selective attention to visual-spatial stimuli causes decrements of power in alpha band and increments in beta. For steady-state visual evoked potentials (SSVEP) selective attention affects electroencephalogram (EEG) recordings, modulating the power in the range 8-27 Hz. The same behaviour can be seen for auditory stimuli as well, although for auditory steady-state response (ASSR), it is not fully confirmed yet. The design of selective attention based braincomputer interfaces (BCIs) has two major advantages: First, no much training is needed. Second, if properly designed, a steady-state response corresponding to spectral peaks can be elicited, easy to filter and classify. In this paper we study the behaviour of Kohonen Maps as feature selector for a selective attention to auditory stimuli based BCI system. [ABSTRACT FROM AUTHOR]

Finding appropriate features is one of the key problems in the increasing applications of rough set theory, which is also one of the bottlenecks of the rough set methodology. Particle Swarm Optimization (PSO) is particularly attractive for this challenging problem. In this paper, we attempt to solve the problem using a particle swarm optimization approach. The proposed approach discover the best feature combinations in an efficient way to observe the change of positive region as the particles proceed through the search space. We evaluate the performance of the proposed PSO algorithm with Genetic Algorithm (GA). Empirical results indicate that the proposed algorithm could be an ideal approach for solving the feature reduction problem when other algorithms failed to give a better solution. [ABSTRACT FROM AUTHOR]

On chip resource distribution is a problem that, due to its complexity, is susceptible to be solved by using artificial intelligence optimization procedures. In this paper, a Hopfield recurrent neural network and a Boltzmann machine are proposed for searching good solutions. The main challenge of this approach is proposing an energy function to be minimized so it mixes all the problem-related restrictions. Experimental data shows that we can get good enough solutions in a reasonable time using Hopfield nets or close to the global minimum solutions using Boltzmann machines. [ABSTRACT FROM AUTHOR]

This work presents a noise cancellation system suitable for different biomedical signals based on a multilayer artificial neural network(ANN). The proposed method consists of a simple structure similar to the MADALINE neuronal network (Multiple ADAptive LINear Element). This network is a grown artificial neuronal network which allows to optimize the number of nodes of one hidden layer and coefficients of several matrixes. These coefficients matrixes are optimized using the Widrow-Hoff Delta algorithm which requires smaller computational cost than the required by the back-propagation algorithm. The method's performance has been obtained by computing the cross correlation between the input and the output signals to the system. In addition, the signal to interference ratio (SIR) has also been computed. Making use of the aforementioned indexes it has been possible to compare the different classical methods (Filter FIR, biorthogonal Wavelet 6,8, Filtered Adaptive LMS) and the proposed system based on neural multilayer networks . The comparison shows that the ANN-based method is able to better preserve the signal waveform at system output with an improved noise reduction in comparison with traditional techniques. Moreover, the ANN technique is able to reduce a great variety of noise signals present in biomedical recordings, like high frequency noise, white noise, movement artifacts and muscular noise. [ABSTRACT FROM AUTHOR]

One of the main challenges in the information security concerns the introduction of systems able to identify intrusions. In this ambit this work takes place describing a new Intrusion Detection System based on anomaly approach. We realized a system with a hybrid solution between host-based and network-based approaches, and it consisted of two subsystems: a statistical system and a neural one. The features extracted from the network traffic belong only to the IP Header and their trend allows us detecting through a simple visual inspection if an attack occurred. Really the two-tier neural system has to indicate the status of the system. It classifies the traffic of the monitored host, distinguishing the background traffic from the anomalous one. Besides, a very important aspect is that the system is able to classify different instances of the same attack in the same class, establishing which attack occurs. [ABSTRACT FROM AUTHOR]

Psychological studies have shown that emotion and affect influence learning. We employ these findings in a machine-learning meta-parameter context, and dynamically couple an adaptive agent's artificial affect to its action-selection mechanism (Boltzmann β). The agent's performance on two important learning problems is measured. The first consists of learning to cope with two alternating goals. The second consists of learning to prefer a later larger reward (global optimum) for an earlier smaller one (local optimum). Results show that, compared to several control conditions, coupling positive affect to exploitation and negative affect to exploration has several important benefits. In the alternating-goal task, it significantly reduces the agent's "goal-switch search peak". The agent finds its new goal faster. In the second task, artificial affect facilitates convergence to a global instead of a local optimum, while permitting to exploit that local optimum. We conclude that affect-controlled action-selection has adaptation benefits. [ABSTRACT FROM AUTHOR]

Existing algorithms for learning Bayesian network require a lot of computation on high dimensional itemsets which affects reliability, robustness and accuracy of these algorithms and takes up a large amount of time. To address the above problem, we propose a new Bayesian network learning algorithm MRMRG, Max Relevance-Min Redundancy Greedy. MRMRG algorithm is a variant of K2 which is a well-known BN learning algorithm. We also analyze the time complexity of MRMRG. The experimental results show that MRMRG algorithm has much better efficiency. It is also shown that MRMRG algorithm has better accuracy than most of existing learning algorithms for limited sample datasets. [ABSTRACT FROM AUTHOR]

Support Vector Machines (SVMs) with few support vectors are quite desirable, as they have a fast application to new, unseen patterns. In this work we shall study the coefficient structure of the dual representation of SVMs constructed for nonlinearly separable problems through kernel perceptron training. We shall relate them with the margin of their support vectors (SVs) and also with the number of iterations in which these SVs take part. These considerations will lead to a remove-and-retrain procedure for building SVMs with a small number of SVs where both suitably small and large coefficient SVs will be taken out from the training sample. Besides providing a significant SV reduction, our method's computational cost is comparable to that of a single SVM training. [ABSTRACT FROM AUTHOR]

The goal of this work is to present an efficient implementation of the Backpropagation (BP) algorithm to train Artificial Neural Networks with general feedforward topology. This will lead us to the "consecutive retrieval problem" that studies how to arrange efficiently sets into a sequence so that every set appears contiguously in the sequence. The BP implementation is analyzed, comparing efficiency results with another similar tool. Together with the BP implementation, the data description and manipulation features of our toolkit facilitates the development of experiments in numerous fields. [ABSTRACT FROM AUTHOR]

In real life, the task learning is reinforced by the related tasks that we have learned or that we learn at the same time. This scheme applied to Artificial Neural Networks (ANN) is known with the name of Multitask Learning (MTL). So, the information coming from the related secondary tasks provide a bias to the main task, which improves its performances versus a Single-Task Learning (STL) scheme. However, this implies a bigger complexity. Data Editing procedures are used to reduce the algorithmic complexity, obtaining an outstanding samples set from the original set. This edited set gets the performance very fast. In this paper we combine MTL with Data Editing, so we can approach the small samples set training in an MTL scheme. [ABSTRACT FROM AUTHOR]

A system that is capable of retaining learned knowledge and selectively transferring portions of that knowledge as a source of inductive bias during new learning would be a significant advance in artificial intelligence and inductive modeling. We define such a system to be a machine lifelong learning, or ML3 system. This paper makes an initial effort at specifying the scope of ML3 systems and their functional requirements. [ABSTRACT FROM AUTHOR]

A formal definition of task relatedness to theoretically justify multi-task learning (MTL) improvements has remained quite elusive. The implementation of MTL using multi-layer perceptron (MLP) neural networks evoked the notion of related tasks sharing an underlying representation. This assumption of relatedness can sometimes hurt the training process if tasks are not truly related in that way. In this paper we present a novel single-layer perceptron (SLP) approach to selectively achieve knowledge transfer in a multi-tasking scenario by using a different notion of task relatedness. The experimental results show that the proposed scheme largely outperforms single-task learning (STL) using single layer perceptrons, working in a robust way even when not closely related tasks are present. [ABSTRACT FROM AUTHOR]

Incomplete data is a common drawback in many pattern classification applications. A classical way to deal with unknown values is missing data estimation. Most machine learning techniques work well with missing values, but they do not focus the missing data estimation to solve the classification task. This paper presents effective neural network approaches based on Multi-Task Learning (MTL) for pattern classification with missing inputs. These MTL networks are compared with representative procedures used for handling incomplete data on two well-known data sets. The experimental results show the superiority of our approaches with respect to alternative techniques. [ABSTRACT FROM AUTHOR]

This paper presents a first approach to try to determine the weight of a newborn using a set of variables determined uniquely by the mother. The proposed model to approximate the weight is a Radial Basis Function Neural Network (RBFNN) because it has been successfully applied to many real world problems. The problem of determining the weight of a newborn could be very useful by the time of diagnosing the gestational diabetes mellitus, since it can be a risk factor, and also to determine if the newborn is macrosomic. However, the design of RBFNNs is another issue which still remains as a challenge since there is no perfect methodology to design an RBFNN using a reduced data set, keeping the generalization capabilities of the network. Within the many design techniques existing in the literature, the use of clustering algorithms as a first initialization step for the RBF centers is a quite common solution and many approaches have been proposed. The following work presents a comparative of RBFNNs generated using several algorithms recently developed concluding that, although RBFNNs that can approximate a training data set with an acceptable error, further work must be done in order to adapt RBFNN to large dimensional spaces where the generalization capabilities might be lost. [ABSTRACT FROM AUTHOR]

This work presents an application example of text document filtering. We compare the DIMLP neural hybrid model to several machine learning algorithms. The clear advantage of this neural hybrid system is its transparency. In fact, the classification strategy of DIMLPs is almost completely encoded into the extracted rules. During cross-validation trials and in the majority of the situations, DIMLPs demonstrated to be at least as accurate as support vector machines, which is one of the most accurate classifiers of the text categorization domain. In the future, in order to further increase DIMLP accuracy, we believe that common sense knowledge could be easily inserted and refined with the use of symbolic rules. [ABSTRACT FROM AUTHOR]

Many Artificial Neural Networks design algorithms or learning methods imply the minimization of an error objective function. During learning, weight values are updated following a strategy that tends to minimize the final mean error in the Network performance. Weight values are classically seen as a representation of the synaptic weights in biological neurons and their ability to change its value could be interpreted as artificial plasticity inspired by this biological property of neurons. In such a way, metaplasticity is interpreted in this paper as the ability to change the efficiency of artificial plasticity giving more relevance to weight updating of less frequent activations and resting relevance to frequent ones. Modeling this interpretation in the training phase, the hypothesis of an improved training is tested in the Multilayer Perceptron with Backpropagation case. The results show a much more efficient training maintaining the Artificial Neural Network performance. [ABSTRACT FROM AUTHOR]

Predicting HIV resistance to drugs is one of many problems for which bioinformaticians have implemented and trained machine learning methods, such as neural networks. Predicting HIV resistance would be much easier if we could directly use the three-dimensional (3D) structure of the targeted protein sequences, but unfortunately we rarely have enough structural information available to train a neural network. Fur-thermore, prediction of the 3D structure of a protein is not straightforward. However, characteristics related to the 3D structure can be used to train a machine learning algorithm as an alternative to take into account the information of the protein folding in the 3D space. Here, starting from this philosophy, we select the amino acid energies as features to predict HIV drug resistance, using a specific topology of a neural network. In this paper, we demonstrate that the amino acid ener-gies are good features to represent the HIV genotype. In addi-tion, it was shown that Bidirectional Recurrent Neural Networks can be used as an efficient classification method for this prob-lem. The prediction performance that was obtained was greater than or at least comparable to results obtained previously. The accuracies vary between 81.3% and 94.7%. [ABSTRACT FROM AUTHOR]

Further Division of Partition Space (FDPS) is a novel technique for neural network classification. Partition space is a space that is used to categorize data sample after sample, which are mapped by neural network learning. The data partition space, which are divided manually into few parts to categorize samples, can be considered as a line segment in the traditional neural network classification. It is proposed that the performance of neural network classification could be improved by using FDPS. In addition, the data partition space are to be divided into many partitions, which will attach to different classes automatically. Experiment results have shown that this method has favorable performance especially with respect to the optimization speed and the accuracy of classified samples. [ABSTRACT FROM AUTHOR]

We consider a notion of morphism of neural networks and develop its properties. We show how, given any definite logic program P, the least fixed point of the immediate consequence operator TP can be computed by the colimit of a family of neural networks determined by P. [ABSTRACT FROM AUTHOR]

In certain classes of chemical reaction networks (CRN), there may be two stable states. The challenge is to find a model of the CRN such that the stability properties can be predicted. In this paper we consider the problem of building a P-system designed to simulate the CRN in an attempt to determine if the CRN is stable or bistable. We found that for the networks in [2] none of the bistable CRN would have a bistable P-system by stoichiometry alone. The reaction kinetics must be included in the P-system model; the implementation of which has been considered an open problem. In this paper we conclude that a P-system for a CRN in m reactants and n products has at most 2(m2 + mn) membranes and 6(m2 + mn) rules. This suggests that P-system models of a chemical reaction network, including both stoichiometry and reaction kinetics can be built. [ABSTRACT FROM AUTHOR]

Microfluidic systems, which constitute a miniaturization of a conventional laboratory to the dimensions of a chip, are expected to become the key support for a revolution in the world of biology and chemistry. This article proposes a parallel algorithm that uses DNA and such a distributed microfluidic device to generate scheduling grids in polynomial time. Rather than taking a brute force approach, the algorithm presented here uses concatenation and separation operations to gradually build the DNA strings that represent a Multiprocessor Task scheduling problem grids. The microfluidic device used makes for an autonomous system, also enabling it to solve the problem without the need of external control. [ABSTRACT FROM AUTHOR]

Tissue P systems with cell division is a computing model in the framework of Membrane Computing based on intercellular communication and cooperation between neurons. The ability of cell division allows us to obtain an exponential amount of cells in linear time and to design cellular solutions to NP-complete problems in polynomial time. In this paper we present a solution to the Subset Sum problem via a family of such devices. This is the first solution to a numerical NP-complete problem by using tissue P systems with cell division. [ABSTRACT FROM AUTHOR]

We study a Păun's conjecture concerning the unsolvability of NP-complete problems by polarizationless P systems with active membranes in the usual framework, without cooperation, without priorities, without changing labels, using evolution, communication, dissolution and division rules, and working in maximal parallel manner. We also analyse a version of this conjecture where we consider polarizationless P systems working in the minimally parallel manner. [ABSTRACT FROM AUTHOR]

This is a brief survey of spiking neural P systems, a branch of membrane computing recently introduced with motivation from neural computing. Basic ideas, examples, some results, and several research topics are presented. [ABSTRACT FROM AUTHOR]

An architecture for a cortical stimulator with visual neuroprosthetic purposes is presented. This device uses a 3D penetrating multielectrode array, which will be implanted in V1, offering different signal amplitude sets with the programable current source module. This electrode array has been proved for injecting current (charge) in a safety, secure and precise way during animal acute experimentation. The dynamic characteristic of the stimulator provide the possibility to adapt the current level to the different electrodes and tissue impedances. The architectureis based on a microprocessor circuit with programmable waveforms with a transistor based current injection stage. With the proposed system, a wide stimuli set can be used for obtaining the optimal parameters to use in a visual neuroprosthesis using as input a retinomorphic system. The histological results validate the stimulation and implantation procedures. [ABSTRACT FROM AUTHOR]

A comprehensive view of speech and voice technologies is now demanding better and more complex tools amenable of extracting as much knowledge about sound and speech as possible. Many knowledge-extraction tasks from speech and voice share well-known procedures at the algorithmic level under the point of view of bio-inspiration. The same resources employed to decode speech phones may be used in the characterization of the speaker (gender, age, speaking group, etc.). Based on these facts the present paper examines a hierarchy of sound processing levels at the auditory and perceptual levels on the brain neural paths which can be translated into a bio-inspired audio-processing architecture. Through this paper its fundamental characteristics are analyzed in relation with current tendencies in cognitive audio processing. Examples extracted from speech processing applications in the domain of acoustic-phonetics are presented. These may find applicability in speaker's characterization, forensics, and biometry, among others. [ABSTRACT FROM AUTHOR]