Artificial Intelligence for Big Data

Component notations of the neural network

There is a standardized way in which the neural networks are denoted, as follows:

• x₁ and x₂ are inputs (It is also possible to call the activation function on the input layer) 
• There are three layers in this network: the input layer, output layer, and hidden layer. 
• There are two neurons in the input layer corresponding to the input variables. Remember, two neurons are used for illustration. However, in reality we are going to have hundreds of thousands of dimensions and hence input variables. The core concepts of ANN are theoretically applicable to any number of input variables. 
• There are three neurons in the hidden layer (layer 2): (a²₁, a²_2, a²₃).
• The neuron in the final layer produces output ...