Best things of 2015
Here are a few things I appreciated in 2015:
A Look into Machine Learning's First Cheating Scandal
At the end of May, the ImageNet Large Scale Visual Recognition Competition, or LSVRC (currently the word’s top annual computer vision contest) announced that a team had violated competition policies by over-submitting results. The follow-up post named a team from Baidu (the Chinese search giant) as the perpetrators of this offense and explained that Baidu had been banned from submitting results to the ILSVRC for a twelve-month period. MIT Technology review called it “Machine learning’s first cheating scandal.”
Overfitting, Regularization, and Hyperparameters
(This lays the ground work for the next post, which was getting too long to be effective.)
Machine Learning is Magic
Perhaps you have heard of the the sophisticated, elegant Cloud-to-Butt plugin, which searches through the text on a website for the phrase “The Cloud” and replaces it with “My Butt”. This compilation shows some of the most urbane results.
Talking Talking Machines
Talking Machines is currently THE machine learning podcast. Last fall when it started out, I was intrigued that someone was starting a podcast focusing specifically on machine learning. But I didn’t really listen until this summer, which was my loss. Now that I’m catching up on it, I think it’s terrific.
A question anyone starting a blog in 2015 should answer: