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

Training error method #20

Open
scriptandcompile opened this issue Sep 12, 2017 · 1 comment
Open

Training error method #20

scriptandcompile opened this issue Sep 12, 2017 · 1 comment

Comments

@scriptandcompile
Copy link
Collaborator

We might consider encapsulating the concept of a 'trainer' into the neural network just as we encapsulated the idea of a 'activation function' object into the neural layer.

this would leave training and error propogation as the job of the trainer and polymorphic and not something the neural network itself handles directly. This should clean up the issue of the name / enum switch thing while also offering the chance to expand into new training types in the future.

@afshinm
Copy link
Owner

afshinm commented Sep 16, 2017

Seems like a good idea. It makes NeuralNetwork easier to understand. My +1.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

No branches or pull requests

2 participants