Yup. I believe that Jeremy just added it there 
1 Like
Might be answered in later in course
1 Like
Anyone have recommendations of places to practice matrix multiplication to get faster + more fluent, especially with knowing how the dimensions need to line up?
In terms of dimension,
(a x b) @ (b x c) = (a x c)
That is it.
2 Likes
I think this link was shared on fastai before, its really a great interactive tool and helps build intuition http://matrixmultiplication.xyz/
ah I see @lesscomfortable just shared the same link lol 
4 Likes
I use emacs.
3 Likes
I have used vscode for remote machines. there are some extensions which you can install for that
You always have Jeremy and Terrence’s tutorial with you.
For more advanced stuff, go for Rachel’s awesome Computational Linear Algebra.
1 Like
where can I learn about the study group during the weekdays?
Remote VSCode extension:
The extension was based on the TextMate rmate idea.
For remote debugging:
Visual Studio Code (VS Code) + Python ptvsd library for remote debugging Python processes with features like setting breakpoints, stepping to the next breakpoint, etc.
6 Likes
Predict the volume of popcorn sales based on the movie description.
2 Likes
I feel it depends on which part of the range is most important, whether you normalise and how your true distribution looks like. A sigmoid is quite linear in the ‘normally interesting’ middle part of the range.
Can we use the WT103 pre-trained model for Non English languages which have different grammar rules than English?
In case of Sinhala (language of Sri Lanka), we normally use Sinhala and mix it with some English. English words are usually nouns.
I think in this case, I need to build a proper language model first of all.
But I’ll try with WT103 and see how it goes.
I highly recommend using pdb.set_trace() and just stepping through the layers of a model and looking at the dimensions change.
2 Likes
The learned entity embeddings for categorical variables can be used in subsequent tabular-data models. So, that’s one way of using transfer learning for tabular data.
1 Like
Thanks @jeremy, @rachel and all at Fast.ai for another great lesson! The Excel spreadsheet was a great way of visualizing and and getting an understanding what is going on under the hood. Together with going through the layers of a calculations of parameters and activations in the last diagram Jeremy drew. Peeling away the layers like this gives such great insights and builds an intuition that just hasn’t been available to me previously. It all meshes nicely with the previous lessons as we get into a deeper understanding on our way back.
So grateful for you all making this accessible and explaining all the moving parts in such an understandable and succinct way.
Also picked up some neat insights into the power of Excel!
And of course a happy birthday to Jeremy!
6 Likes
5 Likes