Basic Structure of Feedforward Networks

Artificial neural networks try to mimic the behaviour and structure of the brain. As such, they are constructed by basic processing units with multiple inputs and a single output called artificial neurons. 

Larger architectures emerged since then, among them, the feed-forward multilayer perceptron (MLP) network has became the most popular network architecture (Hertz et al. 1991). The disposition of neurons in such ANN is quite different from the disposition in the brain they are disposed in layers with different number of neurons each. Layers are named according to their position in the architecture an MLP network has an input layer, an output layer and one or more hidden layers between them. Interconnection between neurons is accomplished by weighted connections that represent the synaptic efficacy of a biological neuron. 

The way that information flows in a feed-forward network classifies them as hierarchical systems. In such systems, members are categorized by levels, from lowest to highest and they can only communicate from low level to higher but not in the opposite direction. It is worth noting that in a MLP network, input layer neurons do not act as real neurons in the sense that they do not apply an activation function, they act as buffers instead and only distribute the signals coming from outside world to the first hidden layer neurons. 

Neural networks are processing systems that work by feeding in some variables and get an output as response to these inputs. The accuracy of the desired output depends on how well the network learned the input-output relationship during training. 

For supervised training a set of desired outputs is needed, so the network learns by direct comparison of its outputs against the set of expected values on the other hand, unsupervised training does not count with a set of defined outputs, the only available information is the correlation that might exists in input data. With the latter procedure it is expected that the network creates categories from these correlations and be able to output values according to the input category. 

---