【摘要】 人工神经网络(ANN)的泛化特性是其最重要的特性,同时也是最不容易保证的特性。在近二十年ANN的快速发展中,涌现了不少改善ANN泛化特性的方法,但是目前ANN的泛化问题仍然十分突出。本文对现有的ANN泛化特性改善方法进行了归纳整理,将它们归纳在五条改善途径之下,评价和检验了现有改善方法所能达到的水平和存在的不足,并对进一步改善ANN泛化特性的方法和途径进行了展望。更多还原

【Abstract】 The generalization capability of an artificial neural network(ANN)is the most important performance of it,but to obtain the good generalization capability of an ANN is not an easy thing.During about twenty years rapid development of ANN technology,many methods of improving the generalization capability have been proposed,but the generalization problem related to an ANN is still serious.This paper first narrates the existing methods of improving ANN generalization capability,sorting them under five categories.Second,the existing improving methods are evaluated and tested,their capabilities and shortcomings being pointed out.Finally,the concluding remarks are given and the prospective improving methods are discussed.更多还原