Knowledge Engineering in AI

Doctors, Financial Advisors, Mechanical Engineers. In the AI world, these professionals are otherwise known as Human Experts. A human expert has deep knowledge of their respective fields and also posses a superior capability to understand problems related to their domains.

Knowledge engineering is a field of Artificial Intelligence (AI) where “Expert Systems” has designed to emulate Human Experts. Knowledge Engineering replicates the decision-making process of a human expert in a specific domain to solve complex problems of that domain. So an expert system is trained to be a domain expert. But remember this, an expert system is a computer program.

For instance, an expert system emulating an Oncologist, chooses the best treatment for its patients. The system would require expertise and knowledge from information contained in medical journals, textbooks, and drug databases. Expert systems now have commercial applications in fields as diverse as medical diagnosis, petroleum engineering, and financial investing.

The components of an Expert System include:

  • Knowledge Base: To be an expert in a particular field, the most crucial requirement is Knowledge. The quality and accuracy of the knowledge in the knowledge base would be key to the system’s ability to make efficient decisions. The contents of Knowledge Bases generally includes factual information, and past experience combined together

Facts for a knowledge base must be acquired from human experts through interviews and observations. This knowledge is then usually represented in the form of “if-then” rules (production rules): “If some condition is true, then the following inference can be made (or some action taken).” The knowledge base of a major expert system includes thousands of rules. A probability factor is often attached to the conclusion of each production rule and to the ultimate recommendation, because the conclusion is not a certainty.
  • Inference Engine: Inference engine is a component of the expert system that applies logical rules to the knowledge base to deduce new information. This is the component of the expert system that ultimately comes to a decision or solution to a given problem. Inference engine commonly proceeds in two modes, which are:
    • Forward chaining or reasoning: The engine starts with the information that it knows (Initial state) to draw a conclusion (i.e reach Goal state). This approach is also known as data-driven approach because we reach to the goal using available data. It is a bottom-up approach.
    • Backward chaining or reasoning: The engine starts with the goal and works backward, chaining through rules to find known facts that support the goal. It is called a goal-driven approach, as a list of goals decides which rules are selected and used. It is a top-down approach.
Forward Chaining
Backward Chaining
  • User Interface: The interface is the most significant sales aspect of a software product. It is the look-and-feel of the the inner working of the expert system which should be easily navigable by the common man. The design of the user interface for an expert system will depend on the operating environment and the qualifications of the user.

Though there are many drawbacks to Expert Systems. The expertise that a specialist requires to answer tackle issues also relies on collateral knowledge: information that is not central to the given issue but still applied to make judgments. Some people refer to this non-linear way of thinking as gut feeling or intuition leaps which in stark contrast to logical and analytical reasoning.

Despite its drawbacks, Expert Systems (like all other technologies) are created with the intention to supplement human skills.

Expert Systems are widely used everywhere in our society, from giving a basic advise on a specific problem to performing very hard physical tasks. Their main purpose is to provide the solution to a problem when it is needed, sometimes in a matter of seconds. With their use performance has increased in business, science, government and others, because of the knowledge they have and the accurate and quick decisions that they can provide to assist all professionals.



Want to join in on my learning journey? Feel free to subscribe!

Leave a Reply


Your email address will not be published. Required fields are marked *

This site uses Akismet to reduce spam. Learn how your comment data is processed.

%d bloggers like this:
search previous next tag category expand menu location phone mail time cart zoom edit close