Abstract: A Markov Decision Process (MDP) is a natural framework for formulating sequential decision-making problems under uncertainty. In recent years, researchers have greatly advanced algorithms ...

An activation function is an important transformer in a neural network which enables a model to learn non-linearity. Given an input or set of inputs, the output of each node in a neural network is ...

In this tutorial you can learn how the gradient descent algorithm works and implement it from scratch in python. First we look at what linear regression is, then we define the loss function. We learn ...