Title :
A variant of second-order multilayer perceptron and its application to function approximations
Author :
Chiang, Cheng-Chin ; Fu, Hsin-Chia
Author_Institution :
Dept. of Comput. Sci. & Inf. Eng., Nat. Chiao-Tung Univ., Hsinchu, Taiwan
Abstract :
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
Keywords :
feedforward neural nets; function approximation; learning (artificial intelligence); continuous-valued functions; function approximations; learning algorithm; network size; quadratic sigmoid function; second-order characteristics; second-order multilayer perceptron; Application software; Computer science; Costs; Function approximation; Multi-layer neural network; Multilayer perceptrons; Neural networks; Neurons; Nonhomogeneous media; Polynomials;
Conference_Titel :
Neural Networks, 1992. IJCNN., International Joint Conference on
Conference_Location :
Baltimore, MD
Print_ISBN :
0-7803-0559-0
DOI :
10.1109/IJCNN.1992.227087
