An artificial neural network is a network of connected artificial neurons.
Multilayer Perceptron
A multilayer perceptron is a class of artificial neural network composed of multiple layers of perceptrons. Each layer can have several perceptrons in parallel with shared inputs.
Back-Propagation
Back-propagation (BP) is an algorithm that computes the gradient of a loss function with respect to the parameters i.e., weights of a neural network using the chain rule. BP starts from the last layer (output layer), computes the gradient one layer at a time, and moves backward till the input layer.
Computational Graph
A computational graph is a way to represent a neural network using a directed graph. The nodes on the graph can be either an operation or an variable. The edges indicates the direction of computation, e.g., input to an operation.