Waiting for the link to the lecture 6.
Me too… it is about RNN today, interesting topic
stream working great!
can u republish the link please
This is better than NIPS!
It is on at the top of the topic.
sound cuts every 20 sec or so for a sec
Is this the last lecture?
its getting better
I love the jokes Jeremy cracks!
Why do we have to have the extra column instead of just adding another embedding?
What’s the difference between having length 51 vectors and having a length 50 embedding and an extra 1 besides that
Jeremy asked to remind to talk more on using Dropout in training and testing in Pytorch
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.
It checks out.