專利授權區國立清華大學國際產學營運總中心 Operations Center for Industry Collaboration

搜尋專利授權區

關鍵字

» 新增關鍵字

選單

專利授權區

專利授權區
專利名稱(中)	多目標神經網路演化方法及裝置
專利名稱(英)	MULTI-OBJECTIVE NEURAL NETWORK EVOLUTION METHOD AND APPARATUS
專利家族	中華民國：I783594
專利權人	國立清華大學 100.00%
發明人	邱偉育,宋宇倫
技術領域	機械結構,電子電機

專利摘要(中)
一種多目標神經網路演化方法及裝置。所述方法包括下列步驟：在不同的多個環境下訓練多個神經網路群；從各神經網路群的多個神經網路中挑選至少一個神經網路，隨機交換所挑選的神經網路中的至少二神經網路的多個基因，以產生多個混合基因組並用以建構多個混合神經網路；利用多目標基因演算法演化所建構的混合神經網路，並計算演化後各混合神經網路的適應度；以及依據演化後的混合神經網路的適應度，決定適應於多個環境的單一多目標神經網路。

專利摘要(中)

一種多目標神經網路演化方法及裝置。所述方法包括下列步驟：在不同的多個環境下訓練多個神經網路群；從各神經網路群的多個神經網路中挑選至少一個神經網路，隨機交換所挑選的神經網路中的至少二神經網路的多個基因，以產生多個混合基因組並用以建構多個混合神經網路；利用多目標基因演算法演化所建構的混合神經網路，並計算演化後各混合神經網路的適應度；以及依據演化後的混合神經網路的適應度，決定適應於多個環境的單一多目標神經網路。

專利摘要(英)
A multi-objective neural network evolution method and multi-objective neural network evolution apparatus are provided. In the method, multiple neural network groups are trained under different environments, respectively. At least one neural network is selected from multiple neural networks of each neural network group, and multiple genes of at least two of the selected neural networks are randomly exchanged to generate multiple mixed genomes and use the same to construct multiple mixed neural networks. The constructed mixed neural networks are evolved by using a multi-objective genetic algorithm, and a fitness value of each of the evolved mixed neural networks is calculated. A single multi-objective neural network adapted for the multiple environments is determined according to the fitness values of the evolved mixed neural networks.

專利摘要(英)

A multi-objective neural network evolution method and multi-objective neural network evolution apparatus are provided. In the method, multiple neural network groups are trained under different environments, respectively. At least one neural network is selected from multiple neural networks of each neural network group, and multiple genes of at least two of the selected neural networks are randomly exchanged to generate multiple mixed genomes and use the same to construct multiple mixed neural networks. The constructed mixed neural networks are evolved by using a multi-objective genetic algorithm, and a fitness value of each of the evolved mixed neural networks is calculated. A single multi-objective neural network adapted for the multiple environments is determined according to the fitness values of the evolved mixed neural networks.

聯絡資訊
承辦人姓名	李曉琪
承辦人電話	03-5715131 #31061
承辦人Email	hsiaochi@mx.nthu.edu.tw