Lesson 5 : embeddings


I don’t quite understand the bolded part and I noticed that when you matrix multiply
the user weights with user dummies , the user activations ( green color portion ) is the same. Is there any link to the bolded section.


https://course.fast.ai/videos/?lesson=5 ( around 25mins )

Well, here’s the thing. This input, we claim, is this one hot encoded version of user ID number 1, and these activations are the activations for user ID number one. Why is that? Because if you think about it, the matrix multiplication between a one hot encoded vector and some matrix is actually going to find the Nth row of that matrix when the one is in position N. So what we’ve done here is we’ve actually got a matrix multiply that is creating these output activations. But it’s doing it in a very interesting way - it’s effectively finding a particular row in the input matrix.