Question:

In my Artificial Intelligence class, the teacher addressed the subject about neural networks, which in this case, neural networks have layers, such as: input , hidden and output, and the neurons that make them up.

However, he mentioned the term bias which seems to me to be a neuron, however, this term left me more confused in relation to neural networks and I would like to have this question clarified.

Doubt

What would Bias be in relation to neural networks?

Answer:

Simply put, the Bias is a "1" valued input associated with a "b" weight on each neuron. Its function is to increase or decrease the net input, in order to translate the activation function on the axis.

Example:

To approximate a set of points to a line, we use y = a*x + b*1 , where a and b are constant. x an input associated with a weight a and we have a weight b associated with an input 1 .

Now imagine that the network activation function is a linear function.