Chapter 1: Introduction to AI
Introduction:
What is intelligence?
Intelligence is the computational part of the ability to achieve goals in the world.
Intelligence means:
“the capacity to learn and solve problems “, in particular,
• The ability to solve novel problems
• The ability to act rationally
• The ability to act like humans
Definition of AI:
Artificial Intelligence is the science and engineering that is concerned with the theory and practice
of developing systems that exhibit the characteristics we associate with intelligence in human behavior:
perception, natural language processing, reasoning, planning and problem solving, learning and adaption
etc.
The goal of work in artificial intelligence is to build machines that perform tasks normally requiring
human intelligence. ______ Nilsson, Nills J; 1971
Research scientists in AI try to get machines to exhibit behavior that we call intelligent behavior
when we observe it in human beings. __________ Slagle, James R; 1971
Four views of AI:
Views of AI fall into four categories
1. Thinking Humanly
2. Thinking rationally
3. Acting Humanly
4. Acting Rationally
Think like Think
Humans Rationally
Act like Act
Humans Rationally
1
Compiled by:
Ranjan Raj Aryal
Add. Associate Professor
Cosmos College Of Managemant & Technology
1 . Act Humanly: Turing Test:
The Turing Test, proposed by Alan Turing (Turing, 1950), was designed to provide a satisfactory
operational definition of intelligence. Turing defined intelligent behavior as the ability to achieve human-
level performance in all cognitive tasks, sufficient to fool an interrogator.
Roughly speaking, the test he proposed is that the computer should be interrogated by human
via a teletype and passed the test if the interrogator cannot tell if there is a computer or a human at the
end.
2. Thinking Humanly:
Cognitive Science approach:
• Try to get “inside” our minds.
For example, conduct experiments with people to try to “reverse-engineer” how we reason, learning,
remember, predict.
3. Thinking Rationally:
• Represent facts about the world via logic
• Use logical inference as a basis for reasoning about these facts.
[Link] Rationally:
1. Decision Theory/Economics
• Set of future states of the world
• Set of possible actions an agent can take
• Utility = gain to an agent for each action/state pair
• An agent acts rationally if it selects the action that maximizes its “utility” or expected
utility if there is uncertainty
2. Emphasis is on autonomous agent that behave rationally (make the best predictions, take the best
actions)
• On average over time
• Within computational limitations
Applications of Artificial Intelligence:
1. Game playing: Machines that can play certain games e.g. Chess with great mastery mainly through
brute (characterized by an absence of reasoning or intelligence) force computation which gives
ability to look a hundred of thousands of positions per second
2. Speech and character recognition: The ability of computers to recognize voices and writing.
2
Compiled by:
Ranjan Raj Aryal
Add. Associate Professor
Cosmos College Of Managemant & Technology
3. Natural Language Processing: Providing the computer with understanding of the domain of
natural language.
4. Expert System: Systems that are able to make decisions and perform the work of professionals
(human expert) e.g. diagnostic systems in hospitals
5. Robotics: Automation of tasks performed by a mechanical device through predefined programs.
6. Information predictors: For example, in banks, insurance companies, market surveys, whereas
intelligence tools are used to detect trends and predict e. g customer behavior
7. Computer vision and pattern recognition: Computer processing of images from the real world and
recognition of features present in images.
AI and Related fields:
Brief history of AI
1943 McCulloch & Walter Pills: Boolean circuit model of brain
1950 Turing’s “Computing Machinery and Intelligence”
1950s Early AI programs, including Samuel’s checkers program, Newell & Simon’s logic Theorist,
Gelernter’s Geometry Engine.
1956 Dartmouth meeting: “Artificial Intelligence” adopted i.e. birth of AI
1956-58 LISP language developed
1965 Robinson’s complete algorithm for logical reasoning
1966-74 AI discovers computational complexity Neural network research almost disappears
1969-79 Early development of knowledge-based system
3
Compiled by:
Ranjan Raj Aryal
Add. Associate Professor
Cosmos College Of Managemant & Technology
1980-88 Expert system industry booms
1980 AI becomes an industry
1986 Neural network return to popularity
1987 AI becomes a science
1991 AI system beats human chess master
1995 The emergence of intelligent agents
2003 Human-level AI back on the agenda
Definition and Importance of Knowledge:
Knowledge is an abstract term that attempts to capture an individual’s understanding of a given
subject. Knowledge is a subset of information. But it is a subset that has been extracted, filtered or
formatted in a very special way. More specifically, the information we call knowledge is information that
has been subjected to, and passed tests of validation. Common sense knowledge is information that has
been validated by common sense experience.
Solving problems in a particular domain generally requires knowledge of the objects in the domain
and knowledge of how to reason in that domain. The importance of domain knowledge in the area of
understanding of domain knowledge in the area of understanding natural language is also apparent.
Learning:
Learning is any process by which a system improves performance from experience. Learning is an
area of AI that focuses on process of self-improvement. It implies that an organism or machine must be
able to adopt to new situations. This requires knowledge acquisition, inference, updating/ refinement of
knowledge base, acquisition of heuristics, applying faster searches etc.
4
Compiled by:
Ranjan Raj Aryal
Add. Associate Professor
Cosmos College Of Managemant & Technology