节点文献
B_a空间中神经网络和平移网络的逼近
On Approximation by Neural and Translation Networks in B_a Spaces
【摘要】 讨论了具一个隐层单元的神经网络在Ba空间中逼近的特征性定理并给出了逼近估计.对于平移网络,建立了Favard型估计.Orlicz空间中的相应结果均作为应用而给出.
【Abstract】 The characteristic theorem as well as the degree of approximating by neural networks and translation networks, with a single hidden layer in B_a spaces is established. The Favard type estimate is obtained as well. The correspondences of Orlicz spaces are given by one of the applications of B_a spaces.
【关键词】 神经网络;
平移网络;
B_a空间;
逼近;
【Key words】 Neural networks; Translation networks; B_a spaces; Approximation.;
【Key words】 Neural networks; Translation networks; B_a spaces; Approximation.;
【基金】 国家自然科学基金(10471069);浙江省教育厅项目(20030431);浙江省高校青年教师资助项目;宁波市青年基金(2004A620017)资助
- 【文献出处】 数学物理学报 ,Acta Mathematiea Scientia , 编辑部邮箱 ,2005年04期
- 【分类号】O174.41
- 【下载频次】37