Creating and saving models


#1

I believe a having methods like fit and predict like scikitlearn and keras… Etc have would be very helpful especially implementing a method to save the best weighta based on a specific score function like R2 will be very helpful for regression problems


#2

Yes, this is on the roadmap for a future release of PennyLane! :slight_smile:


#3

I have already implemented this in a simple notebook with simple functions.
But there is a mysterious thing
Why does the error rate fluctuate after reaching very low Mean Squarred error and then rise up again!


#4

Hi Kareem, are you able to share your notebook or GitHub repository?


#5

I swear to God that I do love open source projects but I have no control over the data.
believe me, as soon as we finish the submission procedure I will create a pull request or post a link here directly it’s a matter of days nothing more