Distill was a new take at publishing research/ideas in deep learning in a visual way: https://distill.pub/ I love their articles and while it was hard to sustain, the quality of the ones in their are pretty good. They provide some tips and templates on how to develop such visual storytelling articles. - Source: Hacker News / 8 months ago

Explainable AI is far from early stages. Read into anthropic ai’s work in mechanistic interpretability like toy models of superposition along with the rest of the transformer-circuits papers. Read chris olah’s distill papers. Read neel nanda’s recent work on reverse engineering how language models grok modular addition. Read kevin meng’s work on locating and editing facts inside of gpt. Read openai’s paper on... Source: 12 months ago

I also wasn't aware of either The Pudding or distill.pub. So thanks for just mentioning those. Source: about 1 year ago

Anything from Setosa [0] is really good. It contains interactive, animated illustrations of several Machine Learning ideas. I _loved_ reading papers from Distill Pub [1] as they contained interactive diagrams. My most favorite one so far is the thread on Differentiable Self-organizing Systems [2]. I liked the lizard example very much as it is interactive, and lizards grow lost organs back. I think this is funny.... - Source: Hacker News / over 1 year ago

If you include deep learning in CS then https://distill.pub/ has a lot to offer in this category. - Source: Hacker News / over 1 year ago

Have you consider dataquest.io ? I m thinking on subscribing there, the learning path since well balanced between theorical and practical knowledge, plus there are some pet projects initiaves. Source: about 1 year ago

I did a lot of planning, reporting and optimizations based on data when I was in digital media, so I've been applying to data focused roles. In my free time, I've also been learning Data Science via dataquest.io, hoping to take my analysis to the next level, learn new skill sets, and keep coding. Source: over 1 year ago

I recommend dataquest.io. It's an intuitive way to learn the fundamentals if you'd rather not study in a more formal manner. Source: over 1 year ago

Does it need to be a postgrad degree? If you want more hands on you might be better using Dataquest. Source: almost 2 years ago

I am using Dataquest to learn Python for Data Science there. I also got a book from O'Riley called Data Science Handbook and the Automating the Boring Stuff with Python book. SQL is good to know and comes in handy. Source: about 2 years ago