Logistic Regression Re-cap

What is Logistic Regression?

Logistic regression is a discriminative probabilistic classification model that operates over real-valued vector inputs. The dimensions of the input vectors being classified are called "features" and there is no restriction against them being correlated. Logistic regression is one of the best probabilistic classifiers, measured in both log loss and first-best classification accuracy across a number of tasks.

Binary logistic regression is equivalent to a one-layer, single-output neural network with a logistic activation function trained under log loss. This is sometimes called classification with a single neuron.

LingPipe: Logistic Regression Tutorial: "Feature Hacking
The joy and curse of feature-based classifiers like logistic regression is that they leave a lot of latitude for "tweaking". Just about anything can be brought in as a feature. With discriminitive models like logistic regression, the features do not even need to be independent."