论文信息 - A variant of second-order multilayer perceptron and its application to function approximations

A variant of second-order multilayer perceptron and its application to function approximations

A second-order multilayer perceptron that uses a different activation function, the quadratic sigmoid function, is proposed. Unlike the conventional sigmoid activation function, the quadratic sigmoid function exhibits second-order characteristics among the input components. Based on this new activation function, a learning algorithm is developed for the new multilayer perceptron. The proposed multilayer perceptron has been used to approximate continuous-valued functions. The approximation results show that the learning speed and the network size were significantly improved in comparison with the conventional multilayer perceptrons which use the sigmoid activation functions.<<ETX>>

Hsin-Chia Fu | Cheng-Chin Chiang | H. Fu | C. Chiang

[1] Yoh-Han Pao,et al. Adaptive pattern recognition and neural networks , 1989 .

[2] F. Girosi,et al. Networks for approximation and learning , 1990, Proc. IEEE.

[3] Christian Lebiere,et al. The Cascade-Correlation Learning Architecture , 1989, NIPS.

[4] Robert A. Jacobs,et al. Increased rates of convergence through learning rate adaptation , 1987, Neural Networks.

[5] Yoshio Hirose,et al. Backpropagation algorithm which varies the number of hidden units , 1989, International 1989 Joint Conference on Neural Networks.

[6] John Moody,et al. Fast Learning in Networks of Locally-Tuned Processing Units , 1989, Neural Computation.

[7] Colin Giles,et al. Learning, invariance, and generalization in high-order neural networks. , 1987, Applied optics.