Jun 25, 2013 — Laplace Smoothing — Why do we need Laplace Smoothing? Let’s return to the problem of using Naive Bayes to classify a recipe as “ice cream”(1) or “sorbet” (2) based on the ingredients (x).  When we are calculating our posterior probabilities, or the probability... Read more

Jun 25, 2013 — Naive Bayes — Naive Bayes is a supervised, probabilistic classification method for discrete classes that makes some strong assumptions about the data, but works pretty well.  If you think back to regression,  regression, we were trying to predict p(y x), and this is... Read more

Jun 22, 2013 — Diffusion Tensor Imaging (DTI) — Diffusion Tensor Imaging looks at white matter integrity.  It is a MRI based method that uses diffusion properties of water molecules to construct white matter fibers (anatomical connections) between brain regions.  There are many metrics of white matter tracts you... Read more

Jun 22, 2013 — K-Means Clustering — K-Means clustering is a bread and butter method of unsupervised clustering in machine learning, and I love it because it’s so intuiitive, and possibly because I learned about it in one of my favorite classes at Stanford, BMI 214 with... Read more