Koshizen T, Fulcher J
Department of Computer Science, University of Wollongong, NSW, Australia.
Int J Neural Syst. 1995 Dec;6(4):425-33. doi: 10.1142/s0129065795000287.
Classical optimal control methods, notably Pontryagin's Maximum (Minimum) Principle (PMP) can be employed, together with Hamiltonians, to determine optimal system weights in Artificial Neural dynamical systems. A new learning rule based on weight equations derived using PMP is shown to be suitable for both discrete- and continuous-time systems, and moreover, can also be applied to feedback networks. Preliminary testing shows that this PMP learning rule compares favorably with Standard BackPropagations (SBP) on the XOR problem.
经典最优控制方法，尤其是庞特里亚金极大值（极小值）原理（PMP），可与哈密顿量一起用于确定人工神经动力学系统中的最优系统权重。一种基于使用PMP推导的权重方程的新学习规则被证明适用于离散时间和连续时间系统，而且还可应用于反馈网络。初步测试表明，在异或问题上，这种PMP学习规则比标准反向传播（SBP）表现更优。
