Week 11 Discussion Thread

This post contains all comments and discussions during our FastBook Week 11 session on convolutions.


Resources

Blog posts from last week

Links from this week

8 Likes

Hi folks! Welcome (back) to Week 11 :smiling_face_with_three_hearts:

9 Likes

I am going to make sure that I write 20 characters. TEST.

3 Likes

This blog article wasn’t completely tied to fastbook, but it was spawned from the Normalization discussion from last week: Normalizing fastai Tabular Inputs | The Problem Solvers Guild

4 Likes

Hi everyone,

Here we are having explicit ratings on a scale of 1-5 or 1-10;

How can we build collab_learner or a recommendation system where we don’t have explicit_ratings but some implicit feedback like number of likes or number of cart adds or number of purchases etc. on a retail website?

Thanks!

Post by Jay Alammar on Embeddings: The Illustrated Word2vec – Jay Alammar – Visualizing machine learning one concept at a time.

Kevin’s Blog: https://blog.problemsolversguild.com/

Convolution Blog: Image Kernels explained visually

3 Likes

Is this collaborative filtering we are discussing?

This was a great read, Thanks for sharing! :slight_smile:

Edit: Please feel free to also share in #projects-resources :tea:

I would probably handle that differently depending on what the distribution of your number of likes looked like. If a lot of posts have 0 likes, but some of them have a large number, you may consider using a scaled version. Another option would be to put them into buckets so bucket 0 would equal 0 likes, bucket 1 would equal 1-10 etc. You could create that rank yourself since it’s just an arbitrary number.

2 Likes

I think using a sigmoid to convert this implicit feedback into some range could be a good rating measure

2 Likes

Yes, I agree. If we have multiple fields though like we want to take into account cart adds, purchases, clicks, likes etc. how can we combine them into one representative rating?

Should it then be a weighted sum of the sigmoids applied to individual features? The main challenge here is sparsity would be more than movies I think because many users buy once or twice and very few users buy frequently for a small online store…

Thanks!

I was checking on ways to address this cold start problem in the FastAI forum. Look at who initiated the discussion! :smiley:

2 Likes

Are Kernels randomly chosen or are they chosen from a limited set that are known to perform well?

2 Likes

kernels are typically initialized with random values. The size of the kernels on the other hand is chosen from a small set (typically) such as 3x3, 5x5, 7x7 - pros/cons for choice of these sizes will become clear as we proceed through the remaining chapters.

1 Like

I liked this blogpost which allows you to play around and understand kernels.
https://setosa.io/ev/image-kernels/

2 Likes

OK. I thought some of the standard image processing ones would be chosen. e.g Kernel (image processing) - Wikipedia

Question from Vasudev S.

What if the values are negative after doing conv operation on the image? How to handle this?

A follow up question: what does the the negative values implies after doing the conv operation on an image?

2 Likes

Just the fact that convolution was not activated at that particular point. For example for top-edge/bottom-edge convolution kernels! But apart from that I am not sure.

1 Like