During quarantine I had more free time than usual so I decided it was time to modernize my blog. I coded the first version 5 years ago choosing technologies simply because I knew them. That resulted in a Django app with...

Last weekend I was coding an application for Twitter timelines analysis which I called Profiler (I was just bored). Some years ago I was working on probabilistic models and there was one which got my attention: ...

Derivatives, specifically gradients (derivatives in more than one dimension spaces) and hesians (second derivatives), have become in a fundamental of machine learning. Gradient is a vector which indicates the maximum slope direction of a function at the evaluated point. This is important to move around the function space to find relative minimums or maximums (to...

Nowadays one of the main problems of any algorithm is its facility to scale it, in other words, its facility to be executed over multiple cores (parallelization) or nodes (distribution). The amount of data that is available today has led the world of computing to develop technologies with which to parallelize and distribute processes are done more easily and...

In this post I'm going to continue explaining concepts that I introduced in previous posts (1 and 2) about Variational inference (VI). Algorithms presented till now have...

In this post I'm going to continue explaining concepts that I introduced in my previous post about Variational Inference (VI). At first I'm going to show that to find the best posterior approach it's necessary to minimize the Kullback-Leibler divergence (KL) between...

In next posts I'm going to speak about probabilistic machine learning. Last months I was learning about this field, specifically about a type of inference on these models known as Variational Inference, and I reckon can be interesting to write a set of posts summarizing my experience about it thanks to my teacher ...