Fast training algorithm for feedforward neural networks: application to crowd estimation at underground stations

Abstract A hybrid fast training algorithm for feedforward networks is proposed. In this algorithm, the weights connecting the last hidden and output layers are firstly evaluated by the least-squares algorithm, whereas the weights between input and hidden layers are evaluated using the modified gradient descent algorithms. The effectiveness of the proposed algorithm is demonstrated by applying it to the sunspot and Mackey–Glass time-series prediction. The results showed that the proposed algorithm can greatly reduce the number of flops required to train the networks. The proposed algorithm is also applied to crowd estimation at underground stations and very promising results are obtained.