Simon Willison’s Weblog

Items tagged machinelearning in 2020

Filters: Year: 2020 × machinelearning ×


How GPT3 Works—Visualizations and Animations. Nice essay full of custom animations illustrating how GPT-3 actually works. # 30th July 2020, 12:58 am

When I was curating my generated tweets, I estimated 30-40% of the tweets were usable comedically, a massive improvement over the 5-10% usability from my GPT-2 tweet generation. However, a 30-40% success rate implies a 60-70% failure rate, which is patently unsuitable for a production application.

Max Woolf # 18th July 2020, 7:33 pm

Tempering Expectations for GPT-3 and OpenAI’s API. Insightful commentary on GPT-3 (which is producing some ridiculously cool demos at the moment thanks to the invite-only OpenAI API) from Max Woolf. # 18th July 2020, 7:29 pm

When data is messy. I love this story: a neural network trained on images was asked what the most significant pixels in pictures of tench (a kind of fish) were: it returned pictures of fingers on a green background, because most of the tench photos it had seen were fisherfolk showing off their catch. # 7th July 2020, 7:03 pm

Data Science is a lot like Harry Potter, except there’s no magic, it’s just math, and instead of a sorting hat you just sort the data with a Python script.

GPT-3, shepherded by Max Woolf # 29th June 2020, 4:45 am

If you have to choose between engineering and ML, choose engineering. It’s easier for great engineers to pick up ML knowledge, but it’s a lot harder for ML experts to become great engineers.

Chip Huyen # 24th June 2020, 5:24 am

Deep learning isn’t hard anymore. This article does a great job of explaining how transfer learning is unlocking a new wave of innovation around deep learning. Previously if you wanted to train a model you needed vast amounts if data and thousands of dollars of compute time. Thanks to transfer learning you can now take an existing model (such as GPT2) and train something useful on top of it that’s specific to a new domain in just minutes it hours, with only a few hundred or a few thousand new labeled samples. # 7th February 2020, 8:47 am

A visual introduction to machine learning. Beautiful interactive essay explaining how a decision tree machine learning module is constructed, and using that to illustrate the concept of overfitting. This is one of the best explanations of machine learning fundamentals I’ve seen anywhere. # 10th January 2020, 5:12 am