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
Yes, this is on the roadmap for a future release of PennyLane!
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!
Hi Kareem, are you able to share your notebook or GitHub repository?
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
We have now added a new KerasLayer feature to PennyLane that converts QNodes to a Keras Layer. This should make it easy to interface more with other elements of Keras.
You can access this feature by installing the latest version of PennyLane:
pip install pennylane --upgrade