The number game, which stems from Josh Tenenbaum’s PhD thesis, illustrates some important ideas about Bayesian concept learning. Here is a discussion of this in lecture notes from Kevin Murphy for reference. The basic setup is as follows: I give you a set of numbers from 1 to 100, and you try to guess another number in the set. For instance, I give … More Turing machines, the number game, and inference
I haven’t updated the blog in a while, as I have been very busy interviewing, going back home for a bit, and transitioning into a new role. I’m proud to say that I’m now working in Mountain View, at the Googleplex! It’s an amazing opportunity to work with some of the top machine learning and statistics researchers … More Hello world from Google!
In the last post I showed how to fit a Bayesian hierarchical model in R to estimate experimental parameters. Our main data analysis pipeline uses Matlab, and we’d like to integrate these two environments for the purpose of analysis. The example involved JAGS, which does have a direct Matlab interface in addition to the more common R one, but more … More Calling R from Matlab – flat file communication
I ran into a tricky problem while analyzing a series of experiments we recently performed with Scanbox. We’re trying to estimate the angle of the objective with respect to the cortical surface. The way we approach this is by scanning at a given depth, going down a little bit, scanning again, and so on. By … More Bayesian mixed effects model to estimate experimental parameters
By far the most popular post on this blog is a review of several Python integrated development environments (IDEs) geared toward science. Coming from a Matlab background, it’s natural to search for something Matlab-like to replace it – an IDE with integrated editor, code execution, plotting, benchmarking, file management, etc. An increasingly attractive alternative is the IPython Notebook. The ipython Notebook … More Scientific Python in the browser: ipython notebook