Abstract
Logistic regression is a method used in classification problems, usually employed as the last layer mapping output to a probability distribution. To be more specific, the logistic regression method is a binary classifier that is often used at the prediction step of a more complicated neural network.
It's a multi-part series in which I am planning to cover the following:
- What is Logistic Regression and Softmax?
- Uses and Advantages
- Sigmoid function
- Weights and Prediction
- Cost function
- Gradient Computation
- Training