回歸相關神經(jīng)網(wǎng)絡的分析與改進
ANALYSIS AND IMPROVEMENT OF RECURRENT CORRELATION NEURAL NETWORKS
-
摘要: 本文分析了回歸相關神經(jīng)網(wǎng)絡容量與動態(tài)范圍之間的關系,指出在一定條件下,回歸相關神經(jīng)網(wǎng)絡具有很高的存儲容量。最后給出了幾種改進網(wǎng)絡性能的方案。Abstract: This paper analyzes the relationship between capacity and dynamics in recurrent correlation neural network, and points out that in some conditions the recurrent correlation neural network has high memory capacity. Then this paper presents several methods for improving the performance.
-
McEliece J R. IEEE Trans. on IT, 1987, IT-33(4): 461-482.[2]Chiueh Tzi-Dar. IEEE Trans. on NN,1991, NN-2(2): 275-284.[3]Zhang Yongjun, Chen Zongzhi. Recurrent Correlation Neural Network loop. IJCNN92, Vo1.2 Beijing: 1992, 109-114. -
計量
- 文章訪問數(shù): 1804
- HTML全文瀏覽量: 99
- PDF下載量: 329
- 被引次數(shù): 0