Artificial Intelligence (AI) and Expert Systems
Artificial Intelligence and Expert Systems
Artificial Intelligence (AI) is a recognized discipline within computer science. It attempts to design software (sometimes with associate hardware) that behaves in a way that, if it were human behavior, would be described as â€œintelligentâ€.
Therefore, Artificial Intelligence is the branch of computer science concerned with making computers behave like human beings, and it can be described as the intelligence of the machines.
The earliest Artificial Intelligence Systems, in the 1960s, concentrated on such activities as playing chess and proving mathematical theorems. However, the techniques are now being applied to aspects of behaviors not normally thought of as requiring great intelligence, such as recognizing objects, understanding simple text, speech recognition and general visual interpretation.
These activities, although often relatively straightforward for people, are, in fact, not so straightforward for computers. It is a challenging problem to write programs for a computer to perform these activities â€“ so much so that we are still far from writing the programs successfully, except in the simplest cases.
One of the recent developments in Artificial Intelligence is neural networks. These draw from and emulate the structure of the brain in terms of neurons. The networks are made to â€˜learnâ€™ from training sessions and then repeat what has been learnt when given new data.
Artificial Intelligence is thus the study and development of computing applications for tasks that would be described as requiring intelligence if they were done by people. Many of these applications involve systems capable of learning, adaption or self-correction.
Cognitive Science covers a wide range of subjects that are concerned with the thinking processes (cognition) and are, to a great extent, people-oriented. Some, such as artificial intelligence, computer vision and human-computer interaction are concerned with computers. Others are concerned with how people function; for example, cognitive psychology, which includes the study of the mental processes of memory, language processing and vision. Some cognitive scientists find it helpful to describe how human function in terms of a computer model of information processing.
Neural net is Artificial Intelligence software that allows a system to learn to recognize features or characteristics of situations that are input to it. The technique is based on a model of the logical properties of interconnected sets of nerve cells.
A neural net is made up of a network of very many junctions or nodes. Each of these nodes will â€˜learnâ€™ features according to its input. Once the learning phase is completed, the neural net can be used to recognize features of the same type that were presented to it originally.
Neural nets have been used for visual recognition and for financial prediction.
Cybernetics is the study of the control of processes by a computer, for example for an industrial process or a robot. Robotics is the study and design of robots.
An Expert System, sometimes also known as an Intelligent Knowledge-Based System (IKBS), is an example of an â€˜intelligentâ€™ system applied to a real-life application. The computer performs at or near level of human experts.
In other words, an Expert System is a computer application that performs a task that would otherwise be performed by a human expert. For example, there are expert systems that can diagnose human illness, make financial forecasts and schedule routes for delivery vehicles. Some expert systems are designed to take place of human experts, while others are designed to aid them.
Thus, in this way, an Expert System can be described as an Artificial Intelligence based system that converts the knowledge of an expert in a specific subject into a software code. This code can be merged with other such codes (based on the knowledge of other experts) and used for answering questions (queries) submitted through a computer.
Expert Systems typically consist of three parts:
- A Knowledge Base which contains the information acquired by interviewing experts, and logic rules that govern how that information is applied.
- An inference engine that interprets the submitted problem against the rules and logic of information stored in the knowledge based.
- An Interface that allows the user to express the problem in a human such as English.