Tuning Fuzzy Perceptron using Parallelized Evolutionary Algorithms
AbstractEvolutionary computation can be used as independent instrument to establish the neural network weights. We assume that the network architecture is known. Some evolutionary algorithms as training procedures of fuzzy perceptron have been proposed before. In this paper, we presented a new hybridization between evolutionary algorithms (used as training procedures of fuzzy perceptron) and parallel algorithms. Using a high performance processor cluster with 28 nodes we will try to get better results in much smaller intervals of time. The kernels used to solve the problem are of the same type, they are eight on each node and each of them is working on the same frequency. The computational results show the validity of new approach in terms runtime, accuracy and flexibility.
How to Cite
Authors retain copyright and grant the journal the right of the first publication with the paper simultaneously licensed under the Creative Commons Attribution 4.0 (CC BY 4.0) licence.
Authors are allowed to enter into separate, additional contractual arrangements for the non-exclusive distribution of the paper published in the journal with an acknowledgement of the initial publication in the journal.
Copyright terms are indicated in the Republic of Lithuania Law on Copyright and Related Rights, Articles 4-37.