Orthogonal neural network is a neural network based on the properties of orthogonal functions. It needs much more processing elements if a small training error is desired. Therefore, numerous data sets are required to train the orthogonal neural network. In the paper, a least square method is proposed to determine the exact weights by applying limited data sets. By using Lagrange interpolation method, the desired data sets required to solve for the exact weights can be calculated. An experiment in approximating typical continuous and discrete functions is given. The Chebyshev polynomial is chosen to generate the processing elements of the orthogonal neural network. The experimental results show that the numerical method in determining the weights has as well performance in approximation error as the known training method and the former has less convergence time.