Saratchandran P
Sch. of Electr. and Electron. Eng., Nanyang Technol. Inst.
IEEE Trans Neural Netw. 1991;2(4):465-7. doi: 10.1109/72.88167.
A novel algorithm for weight adjustments in a multilayer neural network is derived using the principles of dynamic programming. The algorithm computes the optimal values for weights on a layer-by-layer basis starting from the output layer of the network. The advantage of this algorithm is that it provides an error function for every hidden layer expressed entirely in terms of the weights and outputs of the hidden layer, and minimization of this error function yields the optimum weights for the hidden layer.
一种基于动态规划原理推导的用于多层神经网络权重调整的新算法。该算法从网络的输出层开始逐层计算权重的最优值。此算法的优点在于，它为每个隐藏层提供了一个完全由隐藏层的权重和输出表示的误差函数，并且该误差函数的最小化产生隐藏层的最优权重。
