[英]Can I use SQP(Sequential quadratic programming) in scipy for neural network regression optimization?
As title, after training and testing my neural network model in python. 作为标题,在训练和测试我的Python神经网络模型之后。
Can I use SQP function in scipy
for neural network regression problem optimization? 我可以在scipy
使用SQP函数来优化神经网络回归问题吗?
For example, I am using temperature,humid,wind speed ,these three feature for input,predicting energy usage in some area. 例如,我使用温度,湿度,风速这三个功能进行输入,从而预测某些区域的能耗。
So I use neural network to model these input and output's relationship, now I wanna know some energy usage lowest point, what input feature are(ie what temperature,humid,wind seed are).This just example so may sound unrealistic. 因此,我使用神经网络对这些输入和输出之间的关系进行建模,现在我想知道一些能源使用的最低点,什么输入功能(即什么温度,湿度,风能)。这只是一个例子,听起来似乎不切实际。
Because as far as I know, not so many people just use scipy
for neural network optimization. 因为据我所知,没有多少人只是将scipy
用于神经网络优化。 But in some limitation , scipy
is the most ideal optimization tool what I have by now(ps: I can't use cvxopt
). 但是在某些限制下, scipy
是我目前拥有的最理想的优化工具(ps:我不能使用cvxopt
)。
Can someone give me some advice? 有人可以给我一些建议吗? I will be very appreciate! 我将不胜感激!
Sure, that's possible, but your question is too broad to give a complete answer as all details are missing. 当然可以,但是由于缺少所有细节,您的问题过于笼统,无法给出完整的答案。
But: SLSQP is not the right tool! 但是:SLSQP不是正确的工具!
I think you should stick to SGD and it's variants. 我认为您应该坚持使用SGD及其变体。
If you want to go for the second-order approach: learn from sklearn's implementation using LBFGS 如果您想采用二阶方法: 从sklearn的LBFGS实现中学习
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.