查詢結果分析
來源資料
相關文獻
- Artificial Neural Networks with Genetic Algorithm for Human-like Control Technique
- Reinforcement Learning for Ga-Based Neural Networks
- 應用進化式學習架構於人格特質分析--以雲林科大大學生為例
- A GA-based Adaptive Fuzzy System with Reinforcement Learning
- 智慧型非侵入式負載監測系統之設計
- 應用Amazon EC2雲端運算於學習障礙學生鑑定之研究
- 半導體裝機配管工程之成本估價模式
- TLCS:一個有增強式學習能力的分類元系統
- Feature Selection for Classification by Using a GA-based Neural Network Approach
- 企業資源、組織學習環境與知識分享機制對知識移轉績效影響之研究--以基因演算法最佳化之類神經網路對臺灣地區上市上櫃公司加以驗證
頁籤選單縮合
題名 | Artificial Neural Networks with Genetic Algorithm for Human-like Control Technique=類神經網路結合基因演算法之似人控制技術 |
---|---|
作者 | 江青瓚; | 書刊名 | 健行學報 |
卷期 | 19:1 1999.12[民88.12] |
頁次 | 頁37-47 |
分類號 | 312.2 |
關鍵詞 | 智慧型系統; 基因演算法; 類神經元; 學習; Intelligent system; Genetic algorithm; Neuron; Learning; |
語文 | 英文(English) |
中文摘要 | 對於一智慧型系統而言,系統架構之擴展能力是一項非常吸引人且想要擁有的功能,就如同智慧型系統擁有學習能力一般。在此研究中,我們針對此項功能去做探討與開發。在此方法中採用一子集合之類神經元,而基因演算法用來尋找這些類神經元之連結與連結強度。為了使一原有智慧型系統增加一些新的技能,在既有的系統架構中增加新的類神經元。這些新的類神經元間與原有類神經元間之連結與連結強度則採用基因演算法來決定。此方法並不會改變原系統架構,而是增加新類神經元。如此新的學習將會植基於既有(原系統)的技能上。這種結構學習方法會使技能之成長更加有效率。本研究方法不僅僅解決系統功能技術之提升,亦能應用於將高困難度的問題分段學習。 |
英文摘要 | One desirable feature of an intelligent system is the capability of expansion of the system structure as well as the learned techniques. In this study, we investigated the development of such capability. The learning structure consists of a pool of neurons. For a primary skill, a subset of neurons is used. A genetic algorithm is adopted to search for adequate connections and weights for performing the skill. To develop more advanced techniques, unused neurons are selected. The genetic algorithm (GA) is then used to search for connections within the new set of neurons and between the newly selected neurons and the old ones. The original structure is not altered. This preserves the previously learned skills and the new sill can be established based on existent ones. It is expected that, using such hierarchical learning, learning and skill growing can be more efficient. Although the purpose of this study is to resolve the problem of skill expansion upon completing design, it is noted that the scheme can also be applied to relax learning difficulty by decomposing a difficult skill. |
本系統之摘要資訊系依該期刊論文摘要之資訊為主。