I’ve always been enchanted by the notion of encoding real-world entities into lists of numbers. In essence, I believe that hard truth is pristinely objective - like the lyrics of a song - and mathematics is the universe’s all-powerful tool in expressing incontrovertibility.

One aspect I always enjoy about machine learning is that questions often go back to the basics. The field essentially goes into an existential crisis every dozen years—rethinking our tools and asking foundational questions such as “why neural networks” or “why generative models”.1

Version 1.4.10 of RSiteCatalyst brings a handful of new Get* methods, QueueDatawarehouse and a couple of bugs fixes/low-level code improvements.

I broadly believe that the statistics community would benefit from greater exposure to computer science concepts. Consistent with that belief, I argue in this post that the concept of type-safety could be used to develop a normative theory for how statistical computing systems ought to behave. I also argue that such a normative theory would allow us to clarify the ways in which current systems can be misused. Along the way, I note the numerous and profound challenges that any realistic proposal to implement a more type-safe language for statistics would encounter.

Below are two puzzles you might want to try asking your family and friends over the holidays. Try them out yourself, however, first. ||Both questions are simple questions, and both look as though they have obvious answers. Both are questions that, if you think too quickly and go with your gut, you’ll probably get incorrect the first time. Then, if you take a step back, and actually think about them and do the math, you should be able to get the correct answer without too much trouble.Neither of these questions are trick questions. Neither should leave a sour taste in the mouth when the answer is revealed. For both questions, I’ll reveal the answer in stages. After reading the question, give your first answer, then, click on the progressive buttons to reveal the correct answer, and finally the solution and explanation.|

For a few years now I have been experimenting with casting glass and occasionally bronze from 3D printed positive models. Specifically I use this technique to make sculptures of protein molecules rendered as their solvent accessible surface, which are created from their scientifically precise chrystallographic coordinates.

The biggest AI conference of the year has just ended: NIPS in Barcelona broke all records this year and the program was exciting as always. It certainly remains my favorite conference to attend.

If you look through the results on the OpenAI gym, you’ll notice an algorithm that consistently performs well over a wide variety of tasks: Trust Region Policy Optimization, or TRPO for short.