该模型有自组织和自学习的功能，可以根据每次学习误差的不同，不断调整学习速率，加速收敛过程，充分排除数据样本的随机性影响。
The network model can organize and study itself, according to different study error, continuously adjust the study rate, and accelerate refrain process, expel influence of the data sample.
在较为温和的条件下证明了方法的全局收敛性，及罚参数只需进行有限次调整。
It is shown that this method possesses global convergence and the penalty parameters are adjusted only finite times under mild conditions.
该算法能够删除掉冗余的连接甚至节点，通过对网络学习步长的动态调整，避免了算法收敛速度过慢和反复震荡的问题。
The algorithm can remove redundant link even nodes on the network, through the network learning step dynamic adjustment to avoid convergence speed of.
应用推荐