連續(xù)非對稱神經(jīng)網(wǎng)絡(luò)的動力學(xué)特性
DYNAMIC PROPERTIES OF CONTINUOUS UNSYMMETIC NEURAL NETWORKS
-
摘要: 本文討論了連續(xù)非對稱神經(jīng)網(wǎng)絡(luò)的動力學(xué)特性,給出了神經(jīng)網(wǎng)絡(luò)有唯一平衡點(diǎn)的條件,并討論了當(dāng)連接距陣T變化時(shí)不產(chǎn)生靜態(tài)分叉和Hopf分叉的條件,給出了平衡點(diǎn)的全局漸近穩(wěn)定性和全局指數(shù)穩(wěn)定性的充分條件。Abstract: The dynamic properties of continuous unsymmetic neural networks are discussed, and the condition of existence of unique equilibrium point is obtained. The conditions not producing static state bifurcation and Hopf bifurcation are put forward and the sufficient conditions of overall asymptotic stability and exponential stability are obtained.
-
Li J H, Micbel A N, Porod W. IEEE Trans, on CAS, 1988, CAS-35(8); 976-986.[2]Matuoka K. Neural Networks, 1992, 5(3): 995-500.[3]張本想,肖國鎮(zhèn).西安電子科技大學(xué)學(xué)報(bào),1992,19(1): 28-34.[4]蔣耀林,徐建學(xué).非對稱連續(xù)時(shí)間神經(jīng)網(wǎng)絡(luò)系統(tǒng)的穩(wěn)定性分析.中國神經(jīng)網(wǎng)絡(luò)1993年學(xué)術(shù)大會論文集,西安: 228-232.[5]陸啟韶.常微分方程的定性方法和分叉.北京:北京航空航天大學(xué)出版社,1989,231-238,277-278.[6]焦李成.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,1990, 59-67. -
計(jì)量
- 文章訪問數(shù): 1945
- HTML全文瀏覽量: 114
- PDF下載量: 397
- 被引次數(shù): 0
下載:
