I suspect he’ll cover that in the ML class; replacing a “traditional” ML model with a deep learning model shouldn’t change the ensembling step.
1 Like
See the forums where there are a couple of pointers to articles about this.
No fastai. I feel handicapped! 
3 Likes
Sounds great! Thanks @yinterian
Some of the predictions are exceeding five, would this model perform better if the values were capped at zero and five?
8 Likes
How did you decide on the dimension of that matrix? Why 5 rows and not x?
3 Likes
Are those numbers embeddings?
The random numbers
4 Likes
Guess, that’s like features!
embedding for movies and users
1 Like
What are the differences between features and embeddings? Different words same thing?
embeddings are learned
5 Likes
Those features which aren’t explicit! But we want NN to find them for us?
1 Like
features need not necessarily be embeddings. feature could be as simple as ‘is the date a state holiday?’. Embeddings are representations of these features. I think they are the answer to the question : “How can we represent BladeRunner2049 numerically?”
5 Likes
Responding to the question “do you retrain for a new user or new movie?”
At this year’s Grace Hopper many companies mentioned that they approached that problem with the way Jeremy said, i.e., you’d have a specific new user model or new movie model, then retrain over time.
The “what are you interested in?” during onboarding (like meetup.com’s) is a popular approach, but IMO not very friendly if your user is not of your core user group for example.
9 Likes
What does it mean to try different n_factor sizes? Do you train and evaluate using MSE and compare with different embedding sizes given a number of epochs?
Yep, it’s a hyperparameter … so AFAIK no one has worked out a way of automatically picking the best number.
2 Likes
Correct!
1 Like
thanks!
“…wait, what?..”
It’s so comforting that happens to you too @jeremy!
1 Like
Any resource that helps explain a hyperparameter? Thanks in advance