# Tag Archives: machine learning

## Distance between Words

Which pair is more different? keyboard | keyb`ard keyboard | keybpard keyboard | keebored Of course in mathematics we get to decide among many definitions of size and there is no “correct” answer. Just what suits the application. I can … Continue reading

I feel vindicated in several ways by the Netflix Engineering team’s recent blog post explaining what they did with the results of the Netflix Prize. What they wrote confirms what I’ve been saying about recommendations as well as my experience … Continue reading

visualisation of how the kernel trick makes a non-separable collection of points linearly separable. I guess the kernel mappings really add a dimension, rather than replacing a dimension, don’t they. (Source: http://www.youtube.com/)

Upon my return [to academia, after years of private statistical consulting], I started reading the Annals of Statistics … and was bemused. Every article started with: Assume that the data are generated by the following model… followed by mathematics exploring … Continue reading

“The anchovies were nowhere near the sardines and the tuna. That’s because they were near the pizza toppings. But it was only a problem because this was a three-dimensional grocery store. If it had been a thirty-dimensional grocery store they could … Continue reading

## Support Vector Machines and Gender Differences

Earlier I wrote that gender is like a maximally separating hyperplane, including vast within-gender differences? I was trying to use maths to end the war of the sexes. Some who read it didn’t know what a support vector machine was. You … Continue reading

Linear combinations of eigenfaces — images like the above — are the cheapest way to store and search photos of faces. Like if you want to computer analyse the faces of everyone at the Superbowl and see if there’s a … Continue reading

## Recommendation Engines

The Netflix Prize was awarded to the team with the algorithm that most accurately guessed people’s movie tastes. Accurate, according to some measure: root-mean-squared error, or the L2 norm. In my opinion, that’s the wrong measure of success. Netflix selected … Continue reading