Neuron-adaptive higher order neural network group models
Zhang Ming, Shuxiang Xu, Bo Lu · 2003
Neuron-adaptive higher order neural network group (NAHONG) models with a neuron-adaptive activation function are studied in this paper. A learning algorithm is derived to adjust free parameters in the neuron-adaptive activation function as well as connection weights. Our experiments had confirmed that NAHONG model holds superior approximation capabilities to traditional neuron-fixed neural network group model and normal neuron-adaptive neural network group model. Our experiments also reveal that NAHONG is especially exceptional in simulating complex piecewise functions.