The input is used to calculate some intermediate function in the hidden layer, which is then used to calculate an output. 💡 Feedforward Propagation - the flow of information occurs in the forward direction. When learning about neural networks, you will come across two essential terms describing the movement of information-feedforward and backpropagation. The choice depends on the goal or type of prediction made by the model.
However, the output layer will typically use a different activation function from the hidden layers. 📢 Note : All hidden layers usually use the same activation function. It’s the final layer of the network that brings the information learned through the hidden layer and delivers the final value as a result. The hidden layer performs all kinds of computation on the features entered through the input layer and transfers the result to the output layer. They provide an abstraction to the neural network. Hidden LayerĪs the name suggests, the nodes of this layer are not exposed.
Nodes here just pass on the information (features) to the hidden layer. No computation is performed at this layer. The input layer takes raw input from the domain. Each of them is characterized by its weight, bias, and activation function. In the image above, you can see a neural network made of interconnected neurons.