Radek Osmulski
  • Twitter
  • LinkedIn
  • YouTube
  • GitHub
  • My book
  • Projects
  • Twitter threads
  • About

Hey friends —

I'm Radek. I'm a Senior Data Scientist at NVIDIA, a YouTuber and an author.

On this site I write about machine learning techniques and strategies you can use to learn faster.

How did I get here?
Featured

How did I get here?

An introductory chapter to a book on learning machine learning that I wrote.
Nov 9, 2021 3 min read
Use ChatGPT inside Jupyter Notebook
personal project

Use ChatGPT inside Jupyter Notebook

Bringing the new tool as close as possible to where people already do their work is key.
Apr 3, 2023 3 min read
An IDE for the era of AI

An IDE for the era of AI

So much code that I would have to write by hand automagically appears on my screen!
Apr 3, 2023 3 min read
There is something weird about the current generation of AI — better pay attention

There is something weird about the current generation of AI — better pay attention

Hype aside, there is something very uncanny about the most recent generation of AI models.
Mar 27, 2023 3 min read
How to reach the top of the imagenette leaderboard?

How to reach the top of the imagenette leaderboard?

How to make your NNs more shift-invariant? What are some hyperparameter changes worth considering when training with a limited budget of epochs?
Aug 18, 2021 5 min read
Going From Not Being Able to Code to Deep Learning Hero

Going From Not Being Able to Code to Deep Learning Hero

A detailed plan for going from not being able to write code to being a deep learning expert. Advice based on personal experience.
Aug 18, 2021 9 min read
How to build a Deep Learning system that will answer questions about the Harry Potter universe?

How to build a Deep Learning system that will answer questions about the Harry Potter universe?

Riva is a set of APIs into a very complex, very well staffed AI research organization.
Aug 6, 2021 4 min read
20 Years of Tech Startup Experiences in One Hour by Jeremy Howard
notes

20 Years of Tech Startup Experiences in One Hour by Jeremy Howard

There is no such thing as business... there is only such a thing as making things people want and selling them to them.
Jul 29, 2021 3 min read
How to use the power of the community to learn faster

How to use the power of the community to learn faster

Community is the most powerful force behind online learning. It is the reason why MOOCs have a limited impact and tight-knit communities like fast.ai consistently produce unbelievable results.
May 21, 2021 13 min read
How to train and validate on Imagenet
howto

How to train and validate on Imagenet

Training on Imagenet is something that is completely trivial after you do it once, but if you are just someone on the Internet without such prior experience, it is an insurmountable task. Up until a couple of days ago, I didn't even know how to get the data! And then
May 8, 2021 6 min read
Machine Learning and Testing

Machine Learning and Testing

The rewards of testing can be immense, but so can be the price that one would need to pay for testing poorly.
Mar 8, 2019 5 min read
How to train your neural network

How to train your neural network

Evaluation of cosine annealing.
Mar 12, 2018 5 min read
Why take the log of a continuous target variable?

Why take the log of a continuous target variable?

In this article, we’ll look at a simple but useful concept that often gets overlooked.
Mar 5, 2018 4 min read
How to do machine learning efficiently

How to do machine learning efficiently

The only way to maintain your sanity in the long run is to be paranoid in the short run.
Jan 22, 2018 5 min read
Do smoother areas of the error surface lead to better generalization?

Do smoother areas of the error surface lead to better generalization?

An experiment inspired by the first lecture of the fast.ai MOOC
Nov 7, 2017 3 min read
Introduction to data augmentation and pseudo-labeling

Introduction to data augmentation and pseudo-labeling

A closer look at two techniques that can help you make the most of your training data.
Oct 10, 2017 3 min read
Can we beat the state of the art from 2013 with only 0.046% of training examples?

Can we beat the state of the art from 2013 with only 0.046% of training examples?

If we take the CNN layers of a pretrained model, how much data would we need to recover some of the mappings from features to classes? As it turns out, very little!
Sep 23, 2017 3 min read
Automated AWS spot instance provisioning with persisting of data
howto

Automated AWS spot instance provisioning with persisting of data

After following this guide, you will be able to spin up an AWS EC2 spot instance by executing a single command from your terminal. The instance will have a volume attached that will be persisted across shutdowns.
Sep 15, 2017 7 min read
Page 1 of 1
Radek Osmulski © 2023
Powered by Ghost