However, the training of NNs by conventional back-propagation (BP), i. e. the BP-NNs, has intrinsic vulnerable weakness in slow convergence and local minina.

 
  • 常规的神经网络权值训练算法,例如误差反传算法,存在着收敛速度慢,容易陷入局部极值点等问题。
今日热词
目录 附录 查词历史