View profile

Imbalance datasets

Imbalance datasets
By Santiago • Issue #18 • View online
I wrote an article this time, but I’m also linking to a thread I posted on Twitter earlier this week.
I’ve been experimenting with the format of the newsletter. I like the flexibility of linking to different things or writing a dedicated piece just for this.
I want this to be valuable for you. I feel that a fluid format is giving me more options.
What do you think?

How to deal with an imbalanced dataset?
(I love the Dog versus Cat problem. I keep bringing it up, and I’m not sure why.)
Imagine you are trying to build a classification model, and you have two classes: Cats and Dogs.
Unfortunately, there are 950 cat pictures and 50 dog pictures. This is a problem, and understanding how to deal with this is a fundamental skill you’ll have to build.
I wrote an article about it. Here it is:
How to deal with an imbalanced dataset in machine learning?
Thoughts on Copilot
GitHub’s Copilot is as hot 🔥 as it gets.
Before you do anything else, go here and take a look at it. Sign up as soon as you can. Your welcome!
I posted some thoughts about what Copilot means for our industry. If you aren’t in the mood, let me summarize it here for you: Holy shit! It’s a thing!
Software development will never be like this anymore.

Machine learning is changing things as we know them. Today, it's @GitHub's Copilot. What do you think will happen tomorrow?

A thread on sinking buildings and how to stay relevant.
Did you enjoy this issue?

Every week, I’ll teach you something new about machine learning.

Underfitted is for people looking for a bit less theory and a bit more practicality. There's enough mathematical complexity out there already, and you won't find any here.

Come for a journey as I navigate a space that's becoming more popular than Apollo 13, Area 51, and the lousy sequel of Star Wars combined.

If you don't want these updates anymore, please unsubscribe here.
If you were forwarded this newsletter and you like it, you can subscribe here.
Powered by Revue