具有阈值参数的复值神经网络的唯一性定理及参数冗余性
The uniqueness theorem for complex-valued neural networks with threshold parameters and the redundancy of the parameters.
作者信息
Nitta Tohru
机构信息
National Institute of Advanced Industrial Science and Technology, AIST Tsukuba Central 2, 1-1-1 Umezono, Tsukuba-shi, Ibaraki, 305-8568, Japan.
出版信息
Int J Neural Syst. 2008 Apr;18(2):123-34. doi: 10.1142/S0129065708001439.
This paper will prove the uniqueness theorem for 3-layered complex-valued neural networks where the threshold parameters of the hidden neurons can take non-zeros. That is, if a 3-layered complex-valued neural network is irreducible, the 3-layered complex-valued neural network that approximates a given complex-valued function is uniquely determined up to a finite group on the transformations of the learnable parameters of the complex-valued neural network.
本文将证明三层复值神经网络的唯一性定理，其中隐藏神经元的阈值参数可以取非零值。也就是说，如果一个三层复值神经网络是不可约的，那么逼近给定复值函数的三层复值神经网络在复值神经网络可学习参数的变换下，在有限群的意义下是唯一确定的。
Zotero 插件