Particle swarm optimization for neural network learning enhancement

Backpropagation (BP) algorithm is widely used to solve many real world problems by using the concept of Multilayer Perceptron (MLP). However, major disadvantages of BP are its convergence rate is relatively slow and always being trapped at the local minima. To overcome this problem, Genetic Algorith...

全面介紹

Saved in:
書目詳細資料
主要作者: Abdull Hamed, Haza Nuzly
格式: Thesis
語言:English
出版: 2006
主題:
在線閱讀:http://eprints.utm.my/id/eprint/5381/1/HazaNuzlyAbdullHamedMFSKSM2006.pdf
標簽: 添加標簽
沒有標簽, 成為第一個標記此記錄!
實物特徵
總結:Backpropagation (BP) algorithm is widely used to solve many real world problems by using the concept of Multilayer Perceptron (MLP). However, major disadvantages of BP are its convergence rate is relatively slow and always being trapped at the local minima. To overcome this problem, Genetic Algorithm (GA) has been used to determine optimal value for BP parameters such as learning rate and momentum rate and also for weight optimization. In Backpropagation Neural Network (BPNN), there are many elements to be considered such as the number of input, hidden and output nodes, learning rate, momentum rate, bias, minimum error and activation/transfer functions. All these elements will affect the speed of neural network learning. Although GA is successfully improved BPNN learning, there are still some issues such as longer training time to produce the output and usage of complex functions in selection, crossover and mutation calculation. In this study, the latest optimization algorithm, Particle Swarm Optimization (PSO) is chosen and applied in feedforward neural network to enhance the learning process in terms of convergence rate and classification accuracy. Two programs have been developed; Particle Swarm Optimization Feedforward Neural Network (PSONN) and Genetic Algorithm Backpropagation Neural Network (GANN). The results show that PSONN give promising results in term of convergence rate and classification compared to GANN.