Thanks!
isn’t the embedding matrices size match properly or broadcasting is used?
EmbeddingDotBias (
(u): Embedding(671, 50)
(i): Embedding(9066, 50)
(ub): Embedding(671, 1)
(ib): Embedding(9066, 1)
)
I guess fastai still doesn’t support CPU?
Do you mean that the number of users and the number of items (movies) are different, or that they have a different number of factors between the user/item embeddings and the bias embeddings?
The model is running for a single user/movie pair, and uses dense layers to map between the embedding and bias values into a single prediction.
1 Like
It checks out.
10 Likes
1 Like
I Couldn’t find the ‘dislike’ button on the forums for this comment 
Why the transpose of embedding matrix is used for computing PCA?
I assumed that the likes were ironic 
(including mine)
3 Likes
Take a careful look the formula.
1 Like
“Tank girl” is dialog driven?
https://www.movieposter.com/posters/archive/main/95/MPW-47507
Could it be how surreal or satiric the movies are? But then where is Momento?
3 Likes
Where is that formula located?
Correct Answer: https://github.com/fastai/fastai/blob/master/fastai/column_data.py (Line 184)
forward function inside the class.
From the fellows who had done this course previously(this helps a lot)
6 Likes
I’ll make a forum post. I’m still a bit confused.
1 Like
no, look at the collaborative filtering model. Here
class EmbeddingDotBias(nn.Module):
def __init__(self, n_factors, n_users, n_items, min_score, max_score):
super().__init__()
self.min_score,self.max_score = min_score,max_score
(self.u, self.i, self.ub, self.ib) = [get_emb(*o) for o in [
(n_users, n_factors), (n_items, n_factors), (n_users,1), (n_items,1)
]]
def forward(self, users, items):
um = self.u(users)* self.i(items)
res = um.sum(1) + self.ub(users).squeeze() + self.ib(items).squeeze()
return F.sigmoid(res) * (self.max_score-self.min_score) + self.min_score
1 Like
what would be the difference between shallow embedding and deep learning embedding ?
- shallow : get through s dot product matrix multiplication
- deep learning: initiate several layers on the top of a one-hot encoding or any other classic categorical encoding
is it something like this?
Is Shallow learning on large datasets in NLP is faster to get Embeddings than doing a NeuralNet first on?
What was the last question? Didn’t hear it
They were asking about applying some techniques from CV to NLP.
1 Like