The convergence proof for the Perceptron algorithm is one of the most elegant pieces of math I’ve seen in ML. Most useful: Boosting, especially boosted decision trees.

A team of Italian researchers successfully ran a perceptron algorithm on a real, working quantum computer using IBM's cloud-access Q Experience system. Skip to content. Toggle Navigation.

The machine was called the ‘Mark I Perceptron’. It was designed for image recognition and had a camera linked to 20×20 cadmium sulfide photocells to make a 400-pixel image randomly connected to the ...