Artificial Neural Network in AI

What is neural network?

Definition:

According to Dr. Robert Hecht-Nielsen, a neural network is defined as, "A computing system made up of a number of simple, highly interconnected processing elements, which process information by their dynamic state response to external inputs".

• A neural network has the capability of representing the human brain artificially in such a way that it performs the stimulation of its learning process.
• Human brain comprises billions of nerve cells called neurons. These neurons are connected with other cells called as axons.
• In neural network, the stimulation process is carried out with the help of dendrites.
• These dendrites are connected to sensory organs. Thus, the inputs are accepted from external environment by the sensory organs and are passed to dendrites. These inputs create electric impulses and travel through the neural network.
• A neural network consists of a number of nodes, which are connected by links. Each link is associated with a numeric weight.
• Hence, the learning takes place by updating the weights.
• The units which are connected to the external environment can be used as input or output units.
• The simple model shown in the diagram.

In a simple model, the first layer is the input layer, followed by one hidden layer, and lastly by an output layer. Each layer can contain one or more neurons.

Expert System

What is expert system?

• The expert system is a computer program which is developed by using AI technologies to solve the complex problems in a particular field.
• The computer program consists of expert level knowledge to respond properly.
• The expert system should be reliable, highly responsive and understandable.

Components of Expert System

The basic components of an expert system are given below:

1. User interface
It is a software which provides communication access between user and the system.
For example: If an user asks questions, then the system responds with an answer.  

2. Knowledge base
Knowledge base contains expert level knowledge of a particular field that is stored in knowledge representational form. 

3. Inference engine
The Inference engine is a software used to perform the inference reasoning tasks. It uses the knowledge which is stored in the knowledge base and then the information is provided by the user to conclude a new knowledge.

What is shell?

• A shell is a specially designed tool on the basis of  the requirements of particular application.
• Thus,  the user provides the knowledge base to the shell.
  For Example: 
  Shell manages the input and output operations
  Shell processes the information which is provided by the user,and then compares with the concept stored in the knowledge base, and provides the solution for a particular problem.

Benefits of Expert System

Some important benefits of an expert system are listed below:

1. Knowledge Sharing.
2. Reduces errors and inconsistency 
3. Allows non expert users to reach scientifically proven conclusions.