Artificial Intelligence

Dynamic linear models with tfprobability

Welcome to the world of state space models. In this world, there is a latent process, hidden from our eyes; and there are...

Posit AI Blog: TensorFlow feature columns: Transforming your data recipes-style

It’s 2019; no one doubts the effectiveness of deep learning in computer vision. Or natural language processing. With “normal,” Excel-style, a.k.a. tabular data...

Modeling censored data with tfprobability

Nothing’s ever perfect, and data isn’t either. One type of “imperfection” is missing data, where some features are unobserved for some subjects. (A...

Posit AI Blog: Image segmentation with U-Net

Sure, it is nice when I have a picture of some object, and a neural network can tell me what kind of object...

So, how come we can use TensorFlow from R?

Which computer language is most closely associated with TensorFlow? While on the TensorFlow for R blog, we would of course like the answer...

A very first conceptual introduction to Hamiltonian Monte Carlo

Why a very (meaning: VERY!) first conceptual introduction to Hamiltonian Monte Carlo (HMC) on this blog? Well, in our endeavor to feature the various...

Posit AI Blog: TensorFlow 2.0 is here

The wait is over – TensorFlow 2.0 (TF 2) is now officially here! What does this mean for us, users of R packages...

Innocent unicorns considered harmful? How to experiment with GPT-2 from R

When this year in February, OpenAI presented GPT-2(Radford et al. 2019), a large Transformer-based language model trained on an enormous amount of web-scraped...

Posit AI Blog: Variational convnets with tfprobability

A bit more than a year ago, in his beautiful guest post, Nick Strayer showed how to classify a set of everyday activities...

Latest articles