How to convert objection function into maths?

1 view (last 30 days)
Ali
Ali on 15 Jan 2020
Commented: Ali on 28 Jan 2020
I have used Bayesian optimization to optimize the machine learning parameters. The objection fuction is written in MATLAB as:
minfn = @(T)kfoldLoss(XTrain', YTrain', cv, T.hiddenLayerSize,T.LearningRate);
Now i want to convert this objective function into mathematical form.
Any help in this regard would be highly appreciated.

Answers (1)

Athul Prakash
Athul Prakash on 27 Jan 2020
You may run the optimization by calling 'bayesopt' function on 'minfn'. See the doc linked below for more details, the examples might be particularly useful to you.
If you wish to get it in mathematical form, kindly explain exactly what it is you're looking for: do you want to obtain an equation for the optimization problem?.. an equation of the Objective function? Kindly provide some details.
  1 Comment
Ali
Ali on 28 Jan 2020
Thank you athul. I have already gone through from above shared link about Baysopt. I want to contruct an equation for optimization problem based on objective function.
Actually i am optimizing the two neural network parameters (Hidden layers and learning rate) with Bayesopt function. Based on these two parameters aand bayesopt, i want to contruct mathemathical equation to inform other audience what i have done.

Sign in to comment.

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!