refactor neural network code and present an ant code base

[cpetry]

The currently implemented neural network ant has three user programmable parts:

• Creation of the feature vector
• Definition of output (actions)
• Rewarding (Reinforcement learning)

Provide these parts as seperate functions for the user to write code for. Some additional settings could be needed (hidden layers, activation function etc.)

[cpetry]

These seperate function parts could all have their own editor in seperate tabs.