【摘要】 介绍了一种加快神经网络学习的改进算法.这种改进算法结合采用快速自底向上构造神经网络算法和动态优化学习参数算法.首先,快速自底向上构造神经网络算法自动地构建神经网络的优化结构;随后,动态优化学习参数算法动态地调整和选取优化的学习参数.实验结果显示,这种改进算法能自动有效地构造网络的优化结构,与其它算法相比,具有更好的分类性能、优化的网络结构和更快的学习速度.更多还原

【Abstract】 An improved algorithm for speeding up learning of neural networks is proposed.The improved algorithm combines fast cascade-correlation and dynamic optimization of learning parameters.The fast cascade-correlation constructs optimal architecture of neural networks automatically.The dynamic optimization of learning parameters can adjust learning parameters dynamically and select optimal learning parameters.Simulation results show the improved algorithm is able to automatically design optimal neural network with good classification and simple network architecture and fast learning in comparison with other algorithms.更多还原