written 4.6 years ago by |

Neural networks are those information processing systems, which are constructed and implemented to model the human brain. The main objective of the neural network research is to develop a computational device for modelling the brain to perform the various computational task at a faster rate than the traditional system systems. Artificial neural networks perform various stars tasks such as pattern-matching and classification, optimisation function, approximation, vector quantization and data clustering.

**Artificial neural network**

An ANN is an efficient information processing system which resembles in characteristics with a biological neural network. ANN's posses a large number of highly interconnected processing elements called nodes or units or neurons, which usually operate in parallel and are configured in regular architectures.

Each connection link is associated with weights which contains information about the input signal. This information is used by the neuron net to solve a particular problem. ANN's collective behaviour is characterized by their ability to learn, record and generalize training patterns or data similar to that of a human brain. They have the capability to model networks of original neurons as found in the brain. Thus, the ANN processing elements are called **neurons** or **artificial neurons**.

The internal state of the neuron is called the activation or activity level of neurons.

To depict the basic operation of a neural net, consider a set of neurons, say $X_1$ and $X_2$ Signals, and $y$ is the output neuron. $X_1$ and $X_2$ input neurons are connected to the output neuron $Y$, over a weighted interconnections links $ w_1$ and $w_2$. For the below simple neuron net architecture the net input has to be calculated in the following way: $y_{in}=-x_1w_1+x_2w_2$ where $x_1$ and $x_2$ are the activations of the input neurons $X_1$ and $X_2$, i.e., the output of the input signals. The output $y$ of the output neuron $Y$ can be obtained by applying activations over the net input, i.e., the function of the net input; $y=f(y_{in})$

Output= Function (net input calculated)

The function to be applied over the net input is called the **Activation Function**.

Fig: Neural Net of pure linear equation