6 resources that will help you level up. — I never cared much about machine learning. If we were playing the blame game, I’d certainly point to the “math is not my thing” excuse. I had seen it with my own eyes, and it seemed daunting. Back then, we had to write training loops from scratch, beg large universities…

Have you ever tried to understand how you learn new things? This is something that I constantly ask myself. The world moves fast, and staying ahead of the curve requires more than random chance. How do I make sure I’m still moving forward without getting overwhelmed by everything that’s happening? …

I didn’t pay too much attention when I heard about CLIP, a new neural network that learns visual concepts from natural language supervision. At some point, however, my social media feed was all about it. I mostly have to blame this guy. I had to look into it 👀 . …

We were looking for something, but couldn’t find it, so we built it. — Machine learning is a complex subject, so I’m always looking for shortcuts to learn more and stay in touch with the fundamentals. Here is one of those. Something that will help you keep up. A little bit of background I suck at memorizing things. Even when I’m always trying to practice what I learn, it’s…

Contrary to what many believe, a model with the best performance is not necessarily the best choice — Contrary to what many believe, the machine learning model with the best performance is not necessarily the best solution. In Kaggle competitions, performance is all you need. In real-life situations, it’s just another factor to consider. Let’s start with the model's performance and revisit some of the other considerations to…

For over 10 years, I shared a keyboard with him. Here are the things that stuck with me. — He was different, and I was young and eager to learn. In retrospect, I’ve never grown more. The time I’ve spent in school now seems comically useless in comparison. Trying to boil a decade down a few points seems impossible, but I have no choice. Let’s start. Fast is better than good Most of the…

6 different techniques to solve one of the most common problems you’ll face. — A staple in every collection of machine learning interview questions out there, imbalanced datasets are a common problem we need to deal with. Let’s start with an example: Imagine you are trying to build a classification model, and you have two classes: Cats and Dogs. …

About taking action, your approach, communities, and shortcuts. — Right about when the pandemic started, I started helping others divert themselves into machine learning. It was mostly software engineers looking to learn new skills and people migrating from less lucrative careers. I’ve learned a few things in the process. These are 7 lessons that I’d like you to keep…

Think of a factory. Now imagine a machine learning model that looks at a picture of a mechanical component and predicts whether it’s about to break. Don’t worry about how the model does this. Let’s focus on the results instead. Imagine we run 100 pictures through the model, and we…