Quarto 1.3 adds support for embedding cells from a Jupyter Notebook into a Quarto document via an embed shortcode. In HTML documents, links are automatically added that point to a rendered version of the external notebook.
purrr 1.0.0 brings a basket of updates. We deprecated a number of seldom used functions to hone in on the core purpose of purrr and implemented a swath of new features including progress bars, improved error reporting, and much much more!
In dplyr 1.1.0, joins have been greatly reworked, including a new way to specify join columns, support for inequality, rolling, and overlap joins, and two new quality control arguments.
Inside the secret list of websites that make AI like ChatGPT sound smart
An analysis of a chatbot data set by The Washington Post reveals the proprietary, personal, and often offensive websites that go into an AI’s training data.
When performance becomes an issue for code using tidy interfaces, switching to the backend tools used by tidy developers can offer substantial speedups.
AI-enhanced development makes me more ambitious with my projects
The thing I’m most excited about in our weird new AI-enhanced reality is the way it allows me to be more ambitious with my projects. As an experienced developer, ChatGPT …
Visualizing A Neural Machine Translation Model (Mechanics of Seq2seq Models With Attention)
Translations: Chinese (Simplified), French, Japanese, Korean, Persian, Russian, Turkish
Watch: MIT’s Deep Learning State of the Art lecture referencing this post
May 25th update: New graphics (RNN animation, word embedding graph), color coding, elaborated on the final attention example.
Note: The animations below are videos. Touch or hover on them (if you’re using a mouse) to get play controls so you can pause if needed.
Sequence-to-sequence models are deep learning models that have achieved a lot of success in tasks like machine translation, text summarization, and image captioning. Google Translate started using such a model in production in late 2016. These models are explained in the two pioneering papers (Sutskever et al., 2014, Cho et al., 2014).
I found, however, that understanding the model well enough to implement it requires unraveling a series of concepts that build on top of each other. I thought that a bunch of these ideas would be more accessible if expressed visually. That’s what I aim to do in this post. You’ll need some previous understanding of deep learning to get through this post. I hope it can be a useful companion to reading the papers mentioned above (and the attention papers linked later in the post).
A sequence-to-sequence model is a model that takes a sequence of items (words, letters, features of an images…etc) and outputs another sequence of items. A trained model would work like this:
Your browser does not support the video tag.
Significance magazine - Enter our 2023 writing competition for early-career statisticians and data scientists
If you read Significance, then you are definitely interested in stories about statistics and data science, and fascinated by what data can tell us about the world we live in. So, how would you like
