Softmax Regression

Since we had a multi-class dataset, we employed softmax regression. Softmax regression (also known as multinomial logistic regression) is a generalization of logistic regression used for dealing with several classes. As a result, the softmax function performs two tasks: First, it converts all of the scores into probabilities. Then, the total probability equals 1. The sigmoid function is used for the same problem in the binary logistic classifier to classify two classes. The softmax function is little more than a generalized sigmoid function.
