Using Three Layer Neural Networks to Compute Discrete Real Functions
Jian Wang, Yixian Yang, Nan Jiang, Zhaozhi Zhang, Xiaomin Ma · 2007
This paper concerns how to compute discrete real functions using three-layer feedforward neural networks with one hidden layer. Firstly, we define strongly and weakly symmetric real functions. Then we give a network to compute a specific strongly symmetric real function. The number of the hidden neurons is given and the weights of hidden neurons are 1 or -1. Algorithm 1 modifies the weights to real numbers to compute arbitrary strongly symmetric real functions. Theorem 3 extends the results to compute any discrete real functions. Finally, we give an example to indicate our results.