一種改進(jìn)的Elman神經(jīng)網(wǎng)絡(luò)模型
A NEW MODIFIED ELMAN NEURAL NETWORK MODEL
-
摘要: 本文首先詳細(xì)地闡述了Elman神經(jīng)網(wǎng)絡(luò)的結(jié)構(gòu)、原理和學(xué)習(xí)算法.為了進(jìn)一步提高Elman神經(jīng)網(wǎng)絡(luò)的逼近能力和動(dòng)態(tài)特性,我們提出了一種改進(jìn)的Elman神經(jīng)網(wǎng)絡(luò)模型.這種新的Elman神經(jīng)網(wǎng)絡(luò)在關(guān)聯(lián)節(jié)點(diǎn)與輸出節(jié)點(diǎn)之間又增加了一組可調(diào)權(quán)值,利用誤差回饋原理推導(dǎo)出了其相應(yīng)的學(xué)習(xí)算法.仿真實(shí)驗(yàn)結(jié)果表明,改進(jìn)的Elman神經(jīng)網(wǎng)絡(luò)比原來(lái)的網(wǎng)絡(luò)具有更好的動(dòng)態(tài)性能,對(duì)于貫序輸入輸出數(shù)據(jù)的逼近收斂速度更快.Abstract: This paper first discusses the structure, principle and learning algorithm of Elman neural network model. A modified Ehnan neural network model is then proposed by adding new adjustable weights between the context nodes and the output nodes to enhance its dynamical character. The corresponding learning algorithm is also derived by using steepest descent principle. Theoretical analysis and simulation results show that this kind of modified Ehnan neural network learns much faster than the original model.
-
Hunt K J, Sbarbaro D, Zbikowski R, et al.Neural networks for control system-A survey[J].Automatica.1992, 28(6):1083-1112[2]Narendra K S, Parthasarathy K. Identification and control of dynamical systems using neural networks[J].IEEE Trans. on Neural Networks.1990, 1(1):4-27[3]高曉智,王常虹,徐立新,等.CMAC神經(jīng)網(wǎng)絡(luò)再勵(lì)學(xué)習(xí)控制.CIAC95中國(guó)智能自動(dòng)化學(xué)術(shù)會(huì)議里智能自動(dòng)化專業(yè)委員會(huì)成立大會(huì)論文集,天津:1995,638-643.[4]Elman J. Finding structure in time[J].Cognitive Science.1990, 14(2):179-211[5]Sastry P S, Santharam G, Unnikrishnan K P. Memory neuron networks for identification and control of dynamical systems[J].IEEE Trans. on Neural Networks.1994, 5(2):306-319 -
計(jì)量
- 文章訪問(wèn)數(shù): 3024
- HTML全文瀏覽量: 312
- PDF下載量: 476
- 被引次數(shù): 0
下載:
