-
Be like Mike: Michael Jordan’s reading list
Not this Michael Jordan, that Michael Jordan. There’s a machine learning reading list by Michael Jordan that’s been floating around on Hacker News for a few years, and in a recent AMA he added a few more. Full list: Casella, G. and Berger, R.L. (2001). “Statistical Inference” Duxbury Press. Ferguson, T. (1996). “A Course in Large Sample Theory”
-
Extract data directly from websites with import.io
I’ve discussed before how to extract data from static published graphs in Matlab. But what if you wanted to extract table data from a website that doesn’t have an API? import.io does just this. You show a few examples of the data you want to extract from a site, and it guesses intelligently how to extract
-
New paper: sensorimotor integration with travelling waves
Don’t you know about the wave? Everybody knows that the wave is the word. We have a new paper out in Neuron called “A sensorimotor role for traveling waves in visual cortex” (Zanos et al. 2015) [pdf]. Synchronous neuronal activity often propagates parallel to the cortical surface. These traveling waves are a fascinating example of the complex dynamics
-
Machine learning in online dating
Love and happiness It can make you do right, It can make you do wrong It can make you come home early It can make you stay out all night long I went to a LA machine learning meetup last week featuring Jon Morra from eHarmony, where he highlighted some of the uses of machine learning in their online dating platform.
-
The best words in Scrabble
Well, I’m back in the old country for the holidays, and boy do I feel like the smartest pickle in the jar for moving to California when it’s below zero here in Montreal (either scale). There is one thing I miss about the old country: French Scrabble. I’ve spent an inordinate amount of time memorizing
-
Fixing broken .m4v movies made in Matlab
I made a few ten-minute movies in Matlab composed of 1-second clips from BBC Earth, encoded as H.264, to use as visual stimuli. They played fine on Windows but would stop at the 170 second mark in Quicktime on Mac. We’re using Processing on Mac for visual display, which uses Quicktime in the background, so
xcorr: AI & neuro 