rcmnd

Sebastian Ruder

Research scientist at Meta in Berlin working on multilingual models and evaluation; previously led the multilingual team at Cohere and was a research scientist at Google DeepMind.

Also onkorrents, what they believeppll, where they publishwiqqi, who they are

6 things

Deep LearningBook Ian Goodfellow, Yoshua Bengio, Aaron Courville

recommended

Read the Deep Learning book. It is available as a pdf or on Amazon .

His site's FAQ page answering "What resources should I use to get started with Deep Learning?" (undated page; date is the earliest evidence available, the current copy). (undated page)

ruder.io ↗

Speech and Language Processing, 2nd EditionBook Daniel Jurafsky and James H. Martin

recommended

If you're serious about learning NLP, I would recommend to study the fundamentals first by reading Speech and Language Processing, 2nd Edition by Jurafsky and Martin .

His site's FAQ page answering "What resources should I use to get started with Natural Language Processing (NLP)?" (undated page; date is the current copy). (undated page)

ruder.io ↗

Machine Learning (Coursera)Course Andrew Ng

recommended

If you're new to Machine Learning, take the Coursera Machine Learning course by Andrew Ng .

His site's FAQ page answering "What resources should I use to get started with Deep Learning?" (undated page; date is the current copy). (undated page)

ruder.io ↗

fast.ai NLP courseCourse fast.ai

recommended

A great practical and code-first introduction to NLP is the fast.ai NLP course .

His site's FAQ page answering "What resources should I use to get started with Natural Language Processing (NLP)?" (undated page; date is the current copy). (undated page)

ruder.io ↗

Ghost (blogging platform, with GitHub Pages)Software Ghost

uses

I am using Ghost with GitHub Pages , which has worked for me but requires some maintenance.

His site's FAQ page answering "What service or template should I use for starting a blog?" (undated page; date is the current copy). (undated page)

ruder.io ↗

Every entry is a verbatim quote and a link to the public post it came from. Nothing is paraphrased. If it is not on record somewhere public, it is not here.

The verdict is what they actually said: loved and liked are explicit; recommended means they told others to get it; uses means they only say they use it; read is a book on their public shelf with no verdict; mixed and disliked are kept too.

A dashed affiliate link, sponsored or their own label means the post disclosed a relationship. It is shown, never hidden.

The shading behind a date shows how dated a recommendation is for its kind of thing.

The shading behind a date shows how dated a recommendation is, for its kind of thing. Fully green is recent. It drains a quarter at a time as the post gets older, and is empty once it reads as dated.

What counts as old depends on the thing. A laptop praised four years ago has been replaced twice; a book loved twenty years ago is probably still loved. The shading is gone after about:

Stripes mean the post carries no date and the date shown is an estimate. No date at all, no shading.