|
Advantages with neural networks
Computers ability to process logical data, has made them useless to solve non-linear problems.
Until McCulloch and Pitts layed out their theories, people where forced to do things the old way, neural networks seperates itself from
this more conventionel way of programming since:
a. They are non-linear
A neuron itself is not necessarily non-linear, but putted together with other neurons in a network, they enter a compleksity that is able to calculate
non-linear processes, this unlinearity is obviously the most important ability the neural network has.
b. They can relate input with output
Another of the best qualities of neural networks, is the ability to train. With a set of input-output examples and a training algorithm,
you can train your neural network. Read more about this under the learning section.
|
