ABC of Deep Learning (Part 2 of 5)
A Beginner’s Guide to Deep Learning
Previously on …
Ok, we already talked about how the human brain served as the basis for the design of artificial neural networks. In this chapter, when approaching the topic of the activation function, we will better explain the functioning inside the artificial neuron. We will also explain the concept of the cost function, which is important to understand how the learning of artificial neural networks occurs.
The Activation Function
The activation function is used to introduce non-linearity in the model. This is necessary because most real-world data is nonlinear in nature. The activation function allows the model to learn complex patterns in the data. Without the activation function, the model would be linear and unable to learn complex patterns in the data.