Evolutionary Neural Network Based on New Ant Colony Algorithm

• Published in: 2008 International Symposium on Computational Intelligence and Design Vol. 1; pp. 318 - 321
• Main Author: Gao, Wei
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01-10-2008
• Subjects: Algorithm design and analysis; Ant colony optimization; Evolutionary computation; Feedforward neural networks; Feeds; Flowcharts; Genetic algorithms; Genetic programming; Neural networks; Optimization methods
• ISBN: 0769533116; 9780769533117
• DOI: 10.1109/ISCID.2008.143

The evolutionary neural network is the combination of the evolutionary optimization algorithm and traditional neural network. To overcome the demerits of previously proposed evolutionary neural networks, combining the immune continuous ant colony algorithm proposed by author and BP neural network, a new evolutionary neural network whose architecture and connection weights evolve simultaneously is proposed. At last, through the typical XOR problem, the new evolutionary neural network is compared and analyzed with BP neural network, traditional evolutionary neural network based on genetic algorithm and evolutionary neural network based on evolutionary programming. The computing results show that the precision and efficiency of the new evolutionary neural network are all the best.