Relation between input data points and hyper parameters that needs to be tuned

Question

Venkat 2018-8-9

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/414149-relation-between-input-data-points-and-hyper-parameters-that-needs-to-be-tuned

评论： Venkat 2018-8-19

Hi All,

Can anyone please let me know the relationship between the number of input data points and the hyperparameters/number of layers that needs to be present in any machine learning model?

Thanks for your time and help

1 个评论
显示 -1更早的评论隐藏 -1更早的评论

KSSV 2018-8-9

Read about hyperparameters function in matlab.

请先登录，再进行评论。

请先登录，再回答此问题。

Answer 1

Greg Heath 2018-8-9

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/414149-relation-between-input-data-points-and-hyper-parameters-that-needs-to-be-tuned#answer_332101

编辑：Greg Heath 2018-8-9

在 MATLAB Online 中打开

 [ I N]  = size(input)
 [ O N ] = size(target)
 % (MATLAB DEFAULT)
   Ntst    = round(0.15*N)
   Nval    = Ntst
   Ntrn    = N-(Ntst+Nval)%  ~ 0.7*N
 % Design parameters 
   Ndes = Ntrn*O           % No. of design equations ~ 0.7*N*O
   H                       % No. of hidden nodes for I-H-O net
   Nw   = (I+1)*H+(H+1)*O  % No. of unknown weights
 Require  Ndes >= Nw   ==> H <= Hub = (Ntrn*O-O)/(I+O+1)
 Desire   Ndes >> Nw   ==> H << Hub

My typical goal: Minimize H subject to the requirement

MSE < = 0.01*var(target',1) % Rsquare >= 0.99

My approach:

 1. Apply the requirement to the training data
 2. Loop over H to find the minimum H to satisfy the 
    requirement.

I have hundreds of examples in the NEWSGROUP comp.soft-sys.matlab as well as ANSWERS.

Hope this helps

Thank you for formally accepting my answer

Greg

1 个评论
显示 -1更早的评论隐藏 -1更早的评论

Venkat 2018-8-9

Hi Greg,

Thanks for your time and input. I understood what you have said. My problem is I am using CNN. My inputs are images of size 16x512 and I have 30,000 image samples per class, totaling 60,000 representing my 2 classes.

In order to decide on the number of layers in CNN along with the number of filters in each convolutional layer, I am doing an iterative process, but that is going to take a long time. So I am trying to see if I can derive some generic numbers I can start with rather than iterating from 1 to N as far as the number of filters is concerned.

Can I apply the same rule? If yes, can you please explain a little bit more

Thanks

请先登录，再进行评论。