A Fixed-Distribution PAC Learning Theory for Neural FIR Models
作者:Kayvan Najarian
摘要
The PAC learning theory creates a framework to assess the learning properties of static models. This theory has been extended to include learning of modeling tasks with m-dependent data given that the data are distributed according to a uniform distribution. The extended theory can be applied for learning of nonlinear FIR models with the restriction that the data are unformly distributed.
论文关键词:PAC learning, nonlinear FIR model, multi-layer feedforward neural networks, m-dependency
论文评审过程:
论文官网地址:https://doi.org/10.1007/s10844-005-0194-y