Acceleration of the convergence speed of evolutionary algorithms using multi-layer neural networks

Discretization of continuous attributes have played an important role in machine learning and data mining. They can not only improve the performance of the classifier, but also reduce the space of the storage. Univariate Marginal Distribution Algorithm is a modified Evolutionary Algorithms, which has some advantages over classical Evolutionary Algorithms such as the fast convergence speed and few parameters need to be tuned. In this paper, we proposed a bottom-up, global, dynamic, and supervised discretization method on the basis of Univariate Marginal Distribution Algorithm.The experimental results showed that the proposed method could effectively improve the accuracy of classifier.

Download Full-text

Case studies in applying fitness distributions in evolutionary algorithms. II. Comparing the improvements from crossover and Gaussian mutation on simple neural networks

2000 IEEE Symposium on Combinations of Evolutionary Computation and Neural Networks. Proceedings of the First IEEE Symposium on Combinations of Evolutionary Computation and Neural Networks (Cat. No.00EX448) ◽

10.1109/ecnn.2000.886224 ◽

2002 ◽

Cited By ~ 2

Author(s):

A. Jain ◽

D.B. Fogel

Keyword(s):

Neural Networks ◽

Evolutionary Algorithms ◽

Case Studies ◽

Gaussian Mutation

Download Full-text

Designing Radial Basis Function Neural Networks with Meta-Evolutionary Algorithms: The Effect of Chromosome Codification

Distributed Computing, Artificial Intelligence, Bioinformatics, Soft Computing, and Ambient Assisted Living - Lecture Notes in Computer Science ◽

10.1007/978-3-642-02481-8_6 ◽

2009 ◽

pp. 37-40

Author(s):

Elisabet Parras-Gutierrez ◽

Victor M. Rivas ◽

M. Jose del Jesus ◽

Juan J. Merelo

Keyword(s):

Neural Networks ◽

Evolutionary Algorithms ◽

Radial Basis Function ◽

Basis Function ◽

Radial Basis

Download Full-text

Using Particle Swarm Optimization Algorithm as an Optimization Tool Within Developed Neural Networks

Critical Developments and Applications of Swarm Intelligence - Advances in Computational Intelligence and Robotics ◽

10.4018/978-1-5225-5134-8.ch009 ◽

2018 ◽

pp. 215-244

Author(s):

Goran Klepac

Keyword(s):

Neural Network ◽

Neural Networks ◽

Particle Swarm Optimization ◽

Evolutionary Algorithms ◽

Optimization Algorithm ◽

Recommendation System ◽

Particle Swarm Optimization Algorithm ◽

Particle Swarm ◽

Optimal Combination ◽

Swarm Optimization

Developed neural networks as an output could have numerous potential outputs caused by numerous combinations of input values. When we are in position to find optimal combination of input values for achieving specific output value within neural network model it is not a trivial task. This request comes from profiling purposes if, for example, neural network gives information of specific profile regarding input or recommendation system realized by neural networks, etc. Utilizing evolutionary algorithms like particle swarm optimization algorithm, which will be illustrated in this chapter, can solve these problems.

Download Full-text