Determining Topology Architecture for Chaotic Time Series Neural Network
-
摘要: 采用3層前向神經網絡描述混沌時間序列的動力學模型,給出了該網絡拓撲結構的確定方法.以及使網絡泛化誤差達到最小為依據確定網絡的輸入節點和隱含節點個數.仿真結果表明:該方法不僅優化了網絡的結構,而且大大減少了網絡的泛化誤差.Abstract: Three-layered feed-forward neural network is used to establish the model for chaotic time series dynamic systems. Determination method of topology architecture for network is given.The size of the input node and hidden node is determined by the minimization the generalization error of the network. The simulation results show that the network architecture is optimized and the generalization error is dramatically decreased when this method is used.
-
Key words:
- chaotic time series neural network /
- topology architecture /
- generalization error /
-
點擊查看大圖
計量
- 文章訪問數: 282
- HTML全文瀏覽量: 73
- PDF下載量: 6
- 被引次數: 0
下載:
