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

add discussion on transfer learning #39

Open
erinmgraham opened this issue May 31, 2024 · 1 comment
Open

add discussion on transfer learning #39

erinmgraham opened this issue May 31, 2024 · 1 comment
Labels
type:enhancement Propose enhancement to the lesson

Comments

@erinmgraham
Copy link
Collaborator

Ep 06 add discussion on transfer learning and/or give practical examples of where to go to find out how more

@erinmgraham erinmgraham added the type:enhancement Propose enhancement to the lesson label May 31, 2024
@erinmgraham
Copy link
Collaborator Author

Andrew: On transfer learning: there are pretrained models such as ResNet that can be used to for generic classification problems. The pretrained parts of the model can be thought of as being trained to find properties / patterns in images, which then are combined to make new predictions based on these pretrained feature detectors. This would overcome some of the concerns about transfer learning that were raised

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
type:enhancement Propose enhancement to the lesson
Projects
None yet
Development

No branches or pull requests

1 participant