Python Neurolab for neural network

Today, I tried to use Neurolab to build a NN. Many things to learn and consider. Here are some points.


1. The newff output is fixed to range [-1, 1]. If our output is over the range, we should use Norm and Renorm tool.


2. using np to reshape the array


3. predicting: out = net.sim(test_input)


4.There are different training method for "newff".


5. For targets, bad format: targets = [1, 1, 1, 0, 0, 1, 0, 0, 1, 1, 0, 0, 1, 0]. 

                       good one: targets = [[1], [1], [1], [0] ... [0]]



Last, documentation is here: http://pythonhosted.org/neurolab/index.html

google code: https://code.google.com/archive/p/neurolab/


  • 0
    点赞
  • 0
    收藏
    觉得还不错? 一键收藏
  • 0
    评论

“相关推荐”对你有帮助么?

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值