聯(lián)想記憶神經(jīng)網(wǎng)絡(luò)吸收區(qū)域的估計(jì)
ESTIMATION OF ATTRACTION REGION FOR ASSOCIATIVE MEMORY NEURAL NETWORKS
-
摘要: 本文對(duì)于Hopfield型聯(lián)想記憶神經(jīng)網(wǎng)絡(luò)模型,給出了吸收區(qū)域估計(jì)的解析表達(dá)式。這對(duì)于具有多個(gè)平衡位置的網(wǎng)絡(luò)實(shí)現(xiàn)聯(lián)想記憶和優(yōu)化計(jì)算都是重要的問題。
-
關(guān)鍵詞:
- 神經(jīng)網(wǎng)絡(luò); 穩(wěn)定性; 吸收區(qū)域
Abstract: In this paper, the estimation of attraction region for a given equilibrium position of associative memories is given with Lyapunov function method. It is very important for the implementation of associative memories and optimization with neural networks. -
Hopfield J J. Neural networks and physical systms with emergent collective computational abilities[J].Proc. Nat. Acad, Sci. USA.1982, 79:2554-2558[2]Hopfield J J. Neurons with graded response have collective computational properties like those of two-state neurons[J].Proc. Nat. Acad. Sci. USA.1984, 81:3088-3092[3]焦李成,等.神經(jīng)網(wǎng)絡(luò)系統(tǒng)理論.西安:西安電子科技大學(xué)出版社,1991, 1-16.[4]徐秉錚,等編著.神經(jīng)網(wǎng)絡(luò)系統(tǒng)與應(yīng)用.廣州:華南理工大學(xué)出版社,1994, 1-7.[5]Liao Xiaoxin. Stability of Hopfield-type neura networks(I) Science in China(Series A), 1995, 38(4): 407-418.[6]Liao Xiaoxin, Liao Yang. Stability of Hopfield-type neural networks(II), Science in China(Series A), 1997,40(8): 813-816.[7]黃琳.穩(wěn)定性理論.北京:北京大學(xué)出版社,1989,81-88.[8]序曉昕.稚定性的數(shù)學(xué)理論和應(yīng)用.武漢:華中師范大學(xué)出版社,1988, 22-25. -
計(jì)量
- 文章訪問數(shù): 1790
- HTML全文瀏覽量: 85
- PDF下載量: 361
- 被引次數(shù): 0