Yes the current http://
fast.ai course. You missed doing it live but it'll be a MOOC in early 2023. Also our book has a lot of the same stuff.
@jeremyphoward
-
Fast.ai Course Becomes MOOC Early 2023 with Book
By
–
-
Fashion-MNIST: 28×28 Single Channel Image Dataset Overview
By
–
fashion-MNIST images are 28×28 single channel.
-
ImageWoof vs Fashion-MNIST: Neural Network Architecture Considerations
By
–
ImageWoof is much harder, and uses proper RGB images of a useful size! fashion-MNIST is interesting though exactly because they're not normal photographic images. So you gotta think about that carefully when creating your architecture.
-
Challenge Approach: Reimplementing Techniques from Foundations in Python
By
–
(Oh BTW personally for this challenge I'm following the "from the foundations" rules we're using for our current course: only using techniques I've first reimplemented from scratch in pure Python. But y'all can use external libs and stuff if you like…)
-
Company built for task now replaced by Twitter usage
By
–
Yeah we actually made a whole company that does just that… But now I just use Twitter instead.
-
Model Evaluations Counting Details Fine Print Clarification
By
–
Good point – the fine print states we're actually counting model evals
-
Model Evaluation Trade-offs: Epochs vs Computational Budget
By
–
Sure. But you only get to do 60,000*20 model evals in total either way! (i.e if the 2nd order method needs twice as many evals, you only get 10 epochs)
-
Random Initialization Achieving 94% Accuracy in Classification
By
–
If you can find a random initialization that by coincidence happens to get >94% of 60,000 10-class classification decisions correct then yes, that counts.