ELIZA and MYCIN expert system
ELIZA
Eliza was one of the chat-bots in artificial intelligence. It’s a simulation of an Artificial Intelligence Rogerian psychotherapist. This chat-bot demonstrated that how much AI could succeed in mimicking human responses.
Eliza was the first attempt to create a natural language processing computer program from 1964 to 1966 at the MIT Artificial Intelligence Laboratory by Joseph Weizenbaum. It was a method to show the superficiality of communication between man and machine, but was surprised by the number of individuals who attributed human-like feelings to the computer program, including secretary of Weizenbaum. It had no built in framework for contextualizing events. It worked by using a ‘pattern matching’ and substitution methodology that gave users an illusion of understanding on the part of the program.
Eliza listened to what you said and parse the sentence in very basic way, and then ask you question in way that is somehow related to question.in early 1960s people were fooled by Eliza as they thought were told that a real live therapist was talking from the second computer. It was one of the chatterbots that was regarded as one of first programs to pass Turing test.
It was believed that the program would be able to positively influence the lives of many people, particularly those suffering from psychological issues and that it could aid doctors working on such patients’ treatment. Though ELIZA was capable of engaging in discourse, ELIZA could not converse with true understanding. However, many early users were convinced from ELIZA’s intelligence and understanding.
Weizenbaum was shocked by releasing Eliza also known as doctor to the nontechnical staff at the MIT AI Lab. All of the staff of the lab thought that the machine was a real therapist, and spent hours revealing their problems to the program. When Weizenbaum informed his secretary that he had access to logs of all conversations, she was outraged at this invasion of her privacy. He himself was shocked that these kind of simple programs could so easily deceive a native user into revealing personal information.
MYCIN
MYCIN was based on artificial intelligence to identify bacteria that caused several infections and it used to recommend antibiotics, with the dosage adjusted or patient’s body weight. It was also used in diagnoses blood clotting diseases.MYCIN was based on early backward chaining expert system.
· MYCIN was developed at Stanford University in early 1970s over five or six layers.
· The name of MYCIN was derived from antibiotics itself as many antibiotics have the suffix “mycin”.
· Program was written in Lisp.
· It has knowledge base of approximately 600 rules and operated using fairly simple inference engine.
MYCIN was a computer program that was designed to provide attending physicians with the advice that was equivalent to that they would otherwise get from a consulting physician specializing in bacteria and meningitis infections. To use MYCIN, the user must sit in front of a computer that is connected to a DEC-20 (one of Digital Equipment Corporation’s mainframe computers) where the program is stored. When the MYCIN program is educed, a dialogue is initiated. The physician types answers in response to various questions asked. Eventually MYCIN provides a diagnosis and a detailed drug therapy recommendation to the user.
STRUCTURE OF MYCIN PROGRAM:
The system was combination of three major subprograms.
· The Consultation Program
· Explanation Program
· Knowledge Acquisition Program
The Consultation Program is the main of the system; it interacts with the physician to obtain information about the patient, generating diagnoses and give therapy recommendations.
The Explanation Program provides explanations and justifications for the program’s actions.
The Knowledge-Acquisition Program is used by expert to update the system’s knowledge base.
