Lesson 5 In-Class Discussion

https://www.quora.com/What-are-hyperparameters-in-machine-learning

3 Likes

Do we need to check in from romote?

Send an email to Mindi and Leslie

1 Like

A note on collaborative filtering. Iā€™ve found that most people in the industry is using Spark or other distributed framework to do it because in most cases itā€™s a huge matrix decomposition (100M products x 10M customers for instance). Would we be able to use fastai directly or is there a way to customize that?

7 Likes

How is this different from torch.mm(a,b)?

I donā€™t think theyā€™re any different, but Jeremy mentioned he wanted to try to avoid using more abstract libraries if possibleā€¦ so implementing it kind of from scratch to show the intuition behind it

1 Like

International fellows need to check in remotely?

No, you donā€™t have to.

Yes thatā€™s what I was thinking. a*b gives the element-wise product, not dot product. dot product would be torch.mm()

3 Likes

Didnā€™t he sum it to make it dot product? I think it is similar to torch.mm().

The sum gave us a 2x1 matrix.

Dot product of 2x2 and 2x2 matrix should give us 2x2 matrix.

2 Likes

where does n_factors come from in init()?

itā€™s a global variable in this notebook

1 Like

Thanks, seems like an odd way of passing it in ā€¦ but I guess itā€™s not a huge problem.

1 Like

@yinterian Do you have the link to the blog used for initialization?

Yes the dimensions donā€™t match

2 Likes
8 Likes

I agree, but I think itā€™s a consequence of the gap between working in a notebook for exploratory work, then packaging code up for reusability, deployment, and other software engineering goodness.

Jeremy (I think) tweeted out a link to Jake Vanderplasā€™ series called ā€œReproducable Data Analysis in Jupyterā€ that shows a reasonable workflow to move from one to the other. https://www.youtube.com/watch?v=_ZEWDGpM-vM&list=PLYCpMb24GpOC704uO9svUrihl-HY1tTJJ

5 Likes

It may be this one

2 Likes

Could class EmbeddingDot reuse the DotProduct class from before?

3 Likes