Should I add a bias to an artificial neural network that is being trained by a genetic algorithm

Question

I have an ANN that controls an artificial herbivore. The inputs are the closest plant's magnitude and direction, the closest mate's magnitude and direction, and the herbivore's health. The outputs are a movement vector (direction and magnitude). Is it necessary to use a bias if it is being trained by a genetic algorithm?

Answer 1

You have to use bias as it can speed up training and allows the network to learn patterns otherwise, it may not be able to learn. The bias is used to shift the decision boundary of the neural network away from the origin. As per your question, no it is not necessary to use a bias. The network can work without it, but since it's so easy to implement and improves your network, so I will recommend to use it!