我是这个主题的新手,并尝试了一些不同的事情来逃避本地最低要求。我使用随机学习率和动量,但对于一小部分训练,它卡住并且无法学习任何东西(有时卡在开始,有时在中间),即使是随机的起始权重和偏差。
我尝试了几种不同的设置来教授 XOR,例如:
1)Faster learning but with a bigger chance of locally trapped.
(learns in less than 1200 iterations total)
2)Slow learning but with evading local minimum better.
(learns under 40k iterations total)
3)Very steep learning with ~%50 chance of pit-fall(learns under 300 iterations total)
问题:让几个学生参加培训并选择最好的学习者值得吗?或者我们是否需要专注于为单一设置获得 %100 的成功率?
例子:
3 students (XOR candidates) learning in parallel:
-First student is learning fast(learns first, tells others to stop to save cycles)
-Other two are slow learners to increase success rate of training