Abstract
In this work, multilayer perceptron (MLP) has been trained by differential evolution algorithm (DEA) and the performance of the neural network has been analyzed by using high-dimensional and non-linear signature recognition data base. DEA, which doesn't depend on the initial weight values and doesn't stick in local minimums, carries out the global optimization. The performance of the DGA which is the heuristic algorithm to training of the network has been compared to the performance of the error back-propagation algorithm (EBPA) based on gradient. Simulation results show that the performance of the training MLP using DEA is outperforms the training MLP using EBPA.
Keywords
Differential evolution
Training (meteorology)
Computer science
Backpropagation
Signature (topology)
Multilayer perceptron
Heuristic
Algorithm
Artificial neural network
Pattern recognition (psychology)
Perceptron
Base (topology)
Artificial intelligence
Data mining
Mathematics
Physics
Subject Areas
Neural Networks and Applications
·Artificial Intelligence ·Physical Sciences
Advanced Algorithms and Applications
·Control and Systems Engineering ·Physical Sciences
Vehicle License Plate Recognition
·Media Technology ·Physical Sciences
Citations by Year
2015: 1
2017: 1
2023: 1
2024: 3
Loading…
Loading…