徑向基函數(shù)神經(jīng)網(wǎng)絡(luò)的一種有效的在線學(xué)習(xí)方法
AN EFFICIENT ON-LIVE LEARNING METHOD FOR RADIAL BASIS FUNCTION NEURAL KETWORKS
-
摘要: 本文提出了一種徑向基函數(shù)神經(jīng)網(wǎng)絡(luò)的有效在線學(xué)習(xí)方法。該學(xué)習(xí)方法不僅能根據(jù)輸入信息的增加而動態(tài)地分配網(wǎng)絡(luò)資源,而且能有效回收網(wǎng)絡(luò)的冗余資源。在學(xué)習(xí)過程中網(wǎng)絡(luò)的參數(shù)可以自適應(yīng)地序貫進行調(diào)整。文中詳細(xì)論述了這種神經(jīng)網(wǎng)絡(luò)的學(xué)習(xí)準(zhǔn)則、動態(tài)增減隱節(jié)點算法和參數(shù)調(diào)整算法。同時通過分析和實驗說明網(wǎng)絡(luò)具有較強的映射能力和預(yù)測性能。Abstract: This paper proposes an efficient on-line learning method for radial basis function (RBF) neural networks. The proposed learning method not only dynamically allocate the network resource in accordance with the increase of input Information, but also efficiently recycle the redundant resource of the network. During the learning process the parameters of the network can be sequentially adapted. The learning criterion, mechanism of increasing and decreasing resources and the parameter adjustment algorithm are elaborated. Meanwhile both the mapping approximation ability and predication performance of the network are analyzed in details.
-
R.H.Nielsen,Kolmogorov mapping neural network existence theorem.in Proc.Int.Conf.Neural Networks,1987.3.11-13.[2]T.Piggio,F.Girosi,A theory of networks for approximation and learning.AI Memo.No.1140.AI Lab,Massachusetts Institute of Technology,Cambridge Mass:1989. ［3］J.Park,I.W.Sandberg,Universal approximation using radial basis function networks.Neural computation,1991,3(2):246-257.[3]Y.Tan ,Z.Y.He,Arbitrary FIR filter synthesis with neural newwork.Neural Processing Letters,1998,8(1):9-13.[4]A.W.Bruce,et al.Cooperative-competitive genetic evolution of radial basis function centers and widths for time serives prediction.IEEE Trans.on Neural Networks,1996,NN-7(4):869-880.[5]J.Platt,A resonurce-allocating network for function interpolation[J].Neural Computation.1991,3(2):213-225[6]V.Kadirkamanathan,A function estimation approach to sequential learing with neural networks[J].Neural Computation.1993,5(8):954-975[7]Deng Chao,et al.Sequential learning neural networks and its application in agriculture.Proceedings of 1998 IEEE International Joint Conference on Neural Networks(IJCNN98):Alaska,USA:1998,366-370. -
計量
- 文章訪問數(shù): 2182
- HTML全文瀏覽量: 119
- PDF下載量: 358
- 被引次數(shù): 0
下載:
