Multi-Layer Artificial Neural Networks - Artificial intelligence:

Now we can look at more sophisticated ANNs, which are known multi-layer artificial neural networks because they have hidden layers. These will of course be used to undertake more complexes job than perceptrons. First we look at the network structure for multi-layer ANNs, and then at the way in which the weights in such structures can be determined to solve in details machine learning problems. There are several considerations involved with learning such ANNs, and we assumed some of them here. First and foremost, the algorithm may get stuck in local minima, and there are some ways to try to solve out this. As with any learning technique, we will also consider the problem of over fitting, and look which types of problems an ANN approach is fit for.