Jun 30, 2013 — Bayesian MAP Estimate — The **MAP **estimate (maximum a posteriori) estimate is another way to estimate the optimal parameters for a supervised prediction problem.  As a reminder, when we had some training set with features x and labels, y, were using maximum likelihood to... Read more

Jun 29, 2013 — Feature Selection — Science these days is defined by big data.  In economics, medicine, politics, just about any field, we are constantly collecting information about things and trying to build models to understand and predict our world.  In this light, you can imagine... Read more

Jun 29, 2013 — Support Vector Machines (SVMs) — Support Vector Machines (SVMs) **are supervised machine learning classifiers based on the idea that if we plot our data in some n dimensional space, we can draw a **separating hyperplane between the classes.  Based on this description alone, you will... Read more

Jun 27, 2013 — Gaussian Discriminant Analysis (GDA) — Gaussian Discriminant Analysis (GDA) is another generative learning algorithm  that models p(x y) as a multivariate normal distribution.  This means that: The cursive N symbol is used to represent this particular distribution, which represents a nasty looking density equation that is parameterized... Read more