【摘要】 基于梯度算法和前馈网络所具有的普遍近似性质，提出了一种新的监督型多目标系统化训练机制。在学习过程的实现中，该训练机制一方面能使参数集合选择适当以避免过适应，另一方面能以较少的计算及存储复杂度使网络输出达到所要的精度，保证网络具有满意的可检验性和通用性。新的算法（ＰＴＮＴ）能够在一个过程里同时考虑神经网络训练的几个方面，并且在训练时间和准确度方面也都优于ＢＰ算法及其衍生算法。ＰＴＮＴ算法具有类似于ＬＭ算法的收敛性，但存储复杂度远远少于ＬＭ的一半。文中通过仿真结果证明这种监督训练机制和前馈网络在不同问题环境下的适用性，评价了其有效性。更多还原

【Abstract】 Based on gradient algorithm and the fundamental approximation of feedforward network, a new supervised comprehensive training mechanism is put forward. In the realization of learning process, the training mechanism can choose the appropriate parameter set to avoid overfitting, and achieve required accuracy with reduced calculation and storage complexity, as well as satisfactory validity and generality. The new algorithm(PTNT) can incorporate several aspects of the neural network training in the same process, with lessened training process and improved accuracy over BP algorithm and inherited algorithm. PTNT algorithm converges like LM algorithm, with a storage complexity far less than half of the latter. Simulation results justified the generality of the supervised training mechanism and feedforward network.更多还原