Abid S, Fnaiech F, Najim M
IEEE Trans Neural Netw. 2001;12(2):424-30. doi: 10.1109/72.914537.
In this letter, a new approach for the learning process of multilayer feedforward neural network is introduced. This approach minimizes a modified form of the criterion used in the standard backpropagation algorithm. This criterion is based on the sum of the linear and the nonlinear quadratic errors of the output neuron. The quadratic linear error signal is appropriately weighted. The choice of the weighted design parameter is evaluated via rank convergence series analysis and asymptotic constant error values. The new proposed modified standard backpropagation algorithm (MBP) is first derived on a single neuron-based net and then extended to a general feedforward neural network. Simulation results of the 4-b parity checker and the circle in the square problem confirm that the performance of the MBP algorithm exceed the standard backpropagation (SBP) in the reduction of the total number of iterations and in the learning time.
在这封信中，介绍了一种用于多层前馈神经网络学习过程的新方法。这种方法将标准反向传播算法中使用的准则的一种修改形式最小化。该准则基于输出神经元的线性误差和非线性二次误差之和。二次线性误差信号被适当地加权。通过秩收敛级数分析和渐近常数误差值来评估加权设计参数的选择。新提出的改进标准反向传播算法（MBP）首先在基于单个神经元的网络上推导出来，然后扩展到一般的前馈神经网络。4位奇偶校验器和方形中的圆形问题的仿真结果证实，MBP算法在减少总迭代次数和学习时间方面的性能超过了标准反向传播（SBP）算法。
