Skip to content

Conversation

@metavinayak
Copy link

No description provided.

@review-notebook-app
Copy link

Check out this pull request on  ReviewNB

See visual diffs & provide feedback on Jupyter Notebooks.


Powered by ReviewNB

@NippunSharma
Copy link
Owner

@metavinayak great work!!! I see that you have written an automated script (train_model function) that searches for the best set of hyper parameters.
Also, what you did here is a Grid Search on hyperparameters, there are more techniques that can be used to find out the best hyperparameters, some are: Random Search and Bayesian Hyperparameter Optimization (the latter one is a little tough to understand but you can go through how Random Search works).
Maybe you can try adding more layers to the network (maybe you can keep the number of layers in network as a hyperparameter itself!) or you can try changing the number neurons in each layer. I would say to try and automate this also, like what you did for optimizers and activation functions.

Once again, great work!!
Keep us updated on the progress.

@metavinayak
Copy link
Author

Sure I'll look them up.Thanks :)

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants