多层感知器学习算法研究

多层感知器是一种单向传播的多层前馈网络模型，由于具有高度的非线性映射能力，是目前神经网络研究与应用中最基本的网络模型之一．BP算法是多层前向神经网络中应用最重要的算法，但是由于BP算法实质是一种梯度下降的搜索算法，它存在着其固有的不足，如收敛速度较慢，易于陷入误差函数的局部极值．本文基于权值外推和三项因子的思想，提出了一种改进算法，能够有效的提高网络收敛的速度和精度，计算机仿真结果也有力的证实了这一点．

Research on Multilayer Perceptron Learning Algorithm

Multilayer Perceptron is a sort of multilayer feed - forward single direct propagation network model. Because of its good nonlinear mapping ability, it is one of the basic models in the research and application of neural network at present. Multilayer perception trained with BP algorithm often has a low convergence speed as a natural drawback, because it is based on gradient descent method which is only local searching. When applied to an object function with many local minimums, it is not possible for BP algorithm to avoid being trapped in local minimum and to have a low converges speed. In the paper, a new BP algorithm , named TWEBP , which based BPWE and TBP algorithm is presented. Tne results show that the proposed algorithm generally out - performs the conventional algorithm in terms of convergence speed and the ability to escape from local minima.