Luis Fernando de Mingo López

The optimal combination: Grammatical swarm, particle swarm optimization and neural networks

Social behaviour is mainly based on swarm colonies, in which each individual shares its knowledge about the environment with other individuals to get optimal solutions. Such co-operative model differs from competitive models in the way that individuals die and are born by combining information of alive ones. This paper presents the particle swarm optimization with differential evolution algorithm in order to train a neural network instead the classic back propagation algorithm. The performance of a neural network for particular problems is critically dependant on the choice of the processing elements, the net architecture and the learning algorithm. This work is focused in the development of methods for the evolutionary design of artificial neural networks. This paper focuses in optimizing the topology and structure of connectivity for these networks.

Multidimensional knapsack problem optimization using a binary particle swarm model with genetic operations

Particle swarm optimization is a heuristic and stochastic technique inspired by the flock of birds when looking for food. It is currently being used to solve continuous and discrete optimization problems. This paper proposes a hybrid, genetic inspired algorithm that uses random mutation/crossover operations and adds penalty functions to solve a particular case: the multidimensional knapsack problem. The algorithm implementation uses particle swarm for binary variables with a genetic operator. The particles update is performed in the following way: first using the iterative process (standard algorithm) described in the PSO algorithm and then using the best particle position (local) and the best global position to perform a random crossover/mutation with the original particle. The mutation and crossover operations specifically apply to personal and global best individuals. The obtained results are promising compared to those obtained by using the probability binary particle swarm optimization algorithm.Particle swarm optimization is a heuristic and stochastic technique inspired by the flock of birds when looking for food. It is currently being used to solve continuous and discrete optimization problems. This paper proposes a hybrid, genetic inspired algorithm that uses random mutation/crossover operations and adds penalty functions to solve a particular case: the multidimensional knapsack problem. The algorithm implementation uses particle swarm for binary variables with a genetic operator. The particles update is performed in the following way: first using the iterative process (standard algorithm) described in the PSO algorithm and then using the best particle position (local) and the best global position to perform a random crossover/mutation with the original particle. The mutation and crossover operations specifically apply to personal and global best individuals. The obtained results are promising compared to those obtained by using the probability binary particle swarm optimization algorithm.

Natural combination to trade in the stock market

During past 50 years, the markets have been the object of study. Technical and fundamental indicators have been used to try to predict the behavior of the market and then execute buying or selling orders. Neural networks are currently being used with good results although they can be useless after a period of time. This paper proposes an algorithm that combines bioinspired techniques to maximize the hits in the prediction rates. The proposal shown in this paper relies in an ANN to achieve these goals. The differential factors of this approach are the election of the ANN structure with grammatical swarm and the training process through the use of HydroPSO. Also a grammatical swarm algorithm is used to generate trading rules as this method shows better results than the first approach. This combination of techniques provides an automatic way to define the most suitable bioinspired model for the instrument in our analysis.

Data Mining with Enhanced Neural Networks-CMMSE

This paper presents a new method to extract knowledge from existing data sets, that is, to extract symbolic rules using the weights of an Artificial Neural Network. The method has been applied to a neural network with special architecture named Enhanced Neural Network (ENN). This architecture improves the results that have been obtained with multilayer perceptron (MLP). The relationship among the knowledge stored in the weights, the performance of the network and the new implemented algorithm to acquire rules from the weights is explained. The method itself gives a model to follow in the knowledge acquisition with ENN.

Accepting networks of splicing processors with filtered connections

In this paper we simplify accepting networks of splicing processors considered in the paper by Manea et al. by moving the filters from the nodes to the edges. Each edge is viewed as a two-way channel such that input and output filters coincide. Thus, the possibility of controlling the computation in such networks is drastically diminished. In spite of this and of the fact that splicing is not a powerful operation we present here a linear time solution to a much celebrated NP-complete problem, namely SAT, based on these networks viewed as problem solvers. It is worth mentioning that the other resources (number of nodes, symbols, splicing rules, and axioms) of the networks solving instances of SAT are linearly bounded

ACORD: Ant Colony Optimization and BNF Grammar Rule Derivation

Ant Colony Systems have been widely employed in optimization issues primarily focused on path finding optimization, such as Travelling Salesman Problem. The first algorithm was aiming to search for an optimal path in a graph, based on the behavior of ants seeking a path between their colony and a source of food. Besides, ant colony optimization algorithms have been applied to many combinatorial optimization problems, ranging from quadratic assignment to protein folding or routing vehicles and a lot of derived methods have been adapted to dynamic problems in real variables, stochastic problems, multi-targets and parallel implementations. The main advantage lies in the choice of the edge to be explored, defined using the idea of pheromone. This article proposes the use of Ant Colony Systems to explore a Backus-Naur form grammar whose elements are solutions to a given problem. Similar studies, without using Ant Colonies, have been used to solve optimization problems, such as Grammatical Swarm (based on Particle Swarm Optimization) and Grammatical Evolution (based on Genetic Algorithms). Proposed algorithm opens the way to a new branch of research in Swarm Intelligence, which until now has been almost non-existent, using ant colony algorithms to solve problems described by a grammar. (All source code in R is available at https://github.com/fernando-demingo/ACORD-Algorithm).

A String Measure with Symbols Generation: String Self-Organizing Maps

T. Kohonen and P. Somervuo have shown that self organizing maps (SOMs) are not restricted to numerical data. This paper proposes a symbolic measure that is used to implement a string self organizing map based on SOM algorithm. Such measure between two strings is a new string. Computation over strings is performed using a priority relationship among symbols, in this case, symbolic measure is able to generate new symbols. A complementary operation is defined in order to apply such measure to DNA strands. Finally, an algorithm is proposed in order to be able to implement a string self organizing map. This paper discusses the possibility of defining neural networks to rely on similarity instead of distance and shows examples of such networks for symbol strings.

Capacity and Parasitic Fixed Points Control in a Recursive Neural Network

This paper describes a new method for controlling the capacity and for diminishing the number of parasitic fixed points in a Recursive Neural Network RNN. Based on preliminary researches [1] a Recursive Neural Network may be seen as a graph. The matrix of weights W presents certain properties for which it may be called a tetrahedral matrix [2]. The geometrical properties of these kind of matrices may be used for classifying the n-dimensional state-vector space in n classes[2]. In the recall stage, a parameter vector σ may be introduced, which is related with the capacity of the network [3]. It may be shown that the bigger is the value of the i-th component the vector σ the higher became the capacity of the i class of the state-vector space[2]. Once the capacity has been controlled with the parameter σ, we introduce a new parameter that use the statistical deviation of the prototypes to compare them with those that appears as fixed points, eliminating in this way a great number of parasitic fixed points.