Neural Network

• Neural networks are built with an input layer, an output layer, and multiple hidden layers in between. Each layer can contain multiple units. Units in hidden layers can be set arbitrarily.
• Each unit works by multiplying a weight and adding a bias term to the input and going through an activation function. The predicted output is then compared to the actual value using a loss function. A Neural Network works by minimizing that loss by changing the weights and bias terms in each iteration.

• Figure 3: Schematic diagram of a neural network with 2 hidden layers, here both hidden layers has 4 units Figure 4: A single unit in Neural Network