Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Machine learning model #63

Open
emilianbold opened this issue Jan 3, 2018 · 2 comments
Open

Machine learning model #63

emilianbold opened this issue Jan 3, 2018 · 2 comments

Comments

@emilianbold
Copy link
Contributor

I wonder, is there any chances the existing data could be used to maybe predict future values?

We could either show a notification or a hint based on some predicted future state.

@emilianbold
Copy link
Contributor Author

I'm working on the neural network on this branch https://github.com/emilianbold/glucosio-ios/tree/recurrent-neural-network

Right now everything is there, including some debug-only settings to tweak the training.

Still, the network is not training well and I'm not getting good predictions.

Could I get access to some actual values? I'm using my random entries which might be the reason the neural network is unable to train properly or infer anything.

I also found a small bug in the underlying RNN library, although it might also be me mis-using it: Kalvar/ios-RNN#1

@emilianbold
Copy link
Contributor Author

I've implemented a LSTM neural network here https://github.com/emilianbold/swift-lstm

Still, the problem seems to be that with the data I found the results are not very good: the network is not training well and is not predicting well.

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

No branches or pull requests

1 participant