一種通過結(jié)構(gòu)邊界進(jìn)行貝葉斯網(wǎng)絡(luò)學(xué)習(xí)的算法
doi: 10.11999/JEIT140786
基金項目:
國家科技重大專項(2014ZX03006003)資助課題
Learning Bayesian Network from Structure Boundaries
-
摘要: 貝葉斯網(wǎng)絡(luò)是智能算法領(lǐng)域重要的理論工具，其結(jié)構(gòu)學(xué)習(xí)問題被認(rèn)為是NP-hard問題。該文通過混合學(xué)習(xí)算法的方式，從分析低階條件獨立性測試提供的信息入手，給出了構(gòu)造目標(biāo)網(wǎng)絡(luò)結(jié)構(gòu)空間邊界的方法，并給出了完整的證明。在此基礎(chǔ)上執(zhí)行打分搜索算法獲得最終的網(wǎng)絡(luò)結(jié)構(gòu)。仿真結(jié)果表明該算法與同類算法相比具有更高的精度和更好的執(zhí)行效率。
-
關(guān)鍵詞:
- 貝葉斯網(wǎng)絡(luò) /
- 結(jié)構(gòu)學(xué)習(xí) /
- 有向無圈圖 /
- 條件獨立
Abstract: Bayesian network is an important theoretical tool in the artificial algorithm field, and learning structure from data is considered as NP-hard. In this article, a hybrid learning method is proposed by starting from analysis of information provided by low-order conditional independence testing. The methods of constructing boundaries of the structure space of the target network are given, as well as the complete theoretical proof. A search scoring algorithm is operated to find the final structure of the network. Simulation results show that the hybrid learning method proposed in this article has higher learning precision and is more efficient than similar algorithms. -
計量
- 文章訪問數(shù): 1944
- HTML全文瀏覽量: 147
- PDF下載量: 1007
- 被引次數(shù): 0
下載:
