Computing mutual information and other scary things

A moderately technical writeup of some adventures in computing mutual information. I told a colleague of mine, Boris H, of my plan to use mutual information to test data from an experiment. He encouraged me, but he also passed along a warning. "Be wary of discretization. Be very wary" he said, or words to that …

Advertisements

Parzen windows for estimating distributions

Part of a set of moderately technical writeups of some adventures in computing mutual information for neural data. Often, for example, when you are computing mutual information, you need to estimate the probability distribution of a random variable. The simplest way, which I had done for years, is to to create a histogram. You take …

What is machine learning, and why should I care?

This is a (longish) informal intro to machine learning aimed at Biology/Neuroscience undergraduates who are encountering this for the first time in the context of biological data analysis. We are, as you know, furiously lazy. It's a biological adaptation: we always try to find the path of least resistance. Only people with distorted senses of …