The additional sparse features can be incorporated into the linear model, similar to kernel methods used in machine learning. As mentioned, these solutions have now allowed a non-linear decision boundary in conjunction with a linear classifier. In other words, since a straight line could not accurately represent the distribution of our data, we are now able to accurately represent the distribution of the two classes with a non-linear decision boundary, which make take the form of a curved line or multiple lines. But we're representing that non-linear boundary with a linear classifier so that our results will be interpretable.

John Mikhael sees three fields as key to understanding the brain: math, neuroscience, and medicine. "If you want to understand how the brain works, combining those three is a great way to get there," he says. Mikhael, who graduated from MIT in June with a bachelor's degree in mathematics, plans to pursue his study of neuroscience next fall when he enters an MD/PhD program at Oxford University with a Rhodes Scholarship. "Neuroscience is a very exciting field," he says. "In many ways, the brain is the most sophisticated computer out there. Our brains can do things effortlessly that we couldn't even dream of teaching computers how to do, like producing language, understanding social cues, or recognizing faces with our level of proficiency."