An Introduction to AI (CSITNEPAL)
Artificial Intelligence is the study of mental faculties using computational models. In other words, AI is the study of how to make computers do things, which now, the people do better. The fundamental working assumption of AI is:
“What the brain does may be thought of at some kind of computation”
Commonsense Reasoning: includes reasoning about physical objects and their relationships to each other (e.g. an object can be in only one place at a time), as well as reasoning about actions and their consequences (e.g. if a ball is thrown up in air, it will fall down).
The ability to use language to communicate a wide variety of ideas is perhaps the most important thing that separates humans from other animals.
Before going on the study of AI problems and solution techniques, it is important at least to discuss the following queries:
Different definitions of AI are given by different writers. The following definitions can be divided into two dimensions.
Systems that think like humans
“The exciting new effort to make computers think…..machine with minds, in the full and literal sense.” (Haugeland, 1985)
“[The automaton of] activities that we associate with human thinking, activities such as decision-making, problem-solving, learning…..” (Bellman, 1978)
Systems that think rationally
“The study of mental faculties through the use of computational models.” (Charniak and McDermott, 1985)
“The study of the computations that make it possible to perceive, reason, and act.” (Winston, 1992)
Systems that act like humans
“The art of creating machines that perform functions that require intelligence when performed by people.” (Kurzweil, 1990)
“The study of how to make computer do things at which, at the moment, people are better.” (Rich and Knight, 1991)
Systems that act rationally
“Computational Intelligence is the study of the design of intelligent agents.” (Poole et al., 1998)
“AI… is concerned with intelligent behavior in artefacts.” (Nilsson, 1998)
Philosophy includes logic, reasoning, and mind as a physical system, foundations of learning, language and rationality.
˜ From where does knowledge come?
˜ How the knowledge leads to action?
˜ How mental mind arises from physical brain?
˜ Can formal rules be used to draw valid conclusions?
Mathematics include formal representation and proof algorithms, computation, undecidability, intractability, probability.
What are the formal rules that are required to draw the valid conclusions?
What can we compute?
How will we reason with information that are uncertain?
Psychology includes Adaptation, phenomena of perception and motor control.
˜ How do the humans and animals think and act?
Economics includes Formal theory of rational decisions, game theory, operation research.
How should we make decisions so that we can maximize payoff?
How should we do this when others may not go along?
How should we do this when the payoff may be far in future?
Linguistics includes Knowledge representation, grammar
˜ How does the language relate to thought?
Neuroscience includes Physical substrate for mental activities
˜ How do our brains process information?
Control theory includes Homeostatic systems, stability, optimal agent design
˜ How can artifacts be operated under their own control?
Brief history of AI (CSITNEPAL)
– In 1943, Warren Mc Culloch and Walter Pitts built a model of artificial Boolean neurons to perform computations.
– It was First steps toward connectionist computation and learning (Also called Hebbian learning).
–Then Marvin Minsky and Dann Edmonds in 1951 constructed the first neural network computer
–In 1950: Alan Turing’s “Computing Machinery and Intelligence” was built and it was the First complete vision of Artificial Intelligence.
Characteristics of A.I. Programs
- Symbolic Reasoning: reasoning about objects represented by symbols, and their properties and relationships, not just by numerical calculations.
- Knowledge: General principles are stored in the program and used for reasoning about novel situations.
- Search: It is a "weak method'' for finding a solution to a problem when no direct method exists.
- Problem: Problems are combinatorics explosion of possibilities.
- Flexible Control: Direction of processing can be changed by changing facts in the environment.
Applications of AI:
Following are the applications of Artificial Intelligence. In other words, AI are used in following areas:
A theoretical or practical understanding of a subject or a domain is known as knowledge. Also, the sum of what is currently known is what we call “knowledge”.
Knowledge is “the sum of what is known: the body of truth, information, and principles acquired by mankind.” Or, "Knowledge is what I know, Information is what we know."
Knowledge consists of information that has been:
– applied, experienced and revised.
Thus, knowledge in general is more than just data, which consist of: facts, ideas, beliefs, heuristics, associations, rules, abstractions, relationships, and customs.
According to research literature, knowledge is classified as follows:
Classification-based Knowledge » Ability to classify information
Decision-oriented Knowledge » Choosing the best option
Descriptive knowledge » State of some world (heuristic)
Procedural knowledge » How to do something
Reasoning knowledge » What conclusion is valid in what situation?
Assimilative knowledge » What its impact is?
Importance of Knowledge:
In AI for making intelligent machines, knowledge is important. Some key issues confronting the designer of AI system are:
Knowledge acquisition: It is the way of Gathering the knowledge from the problem domain to solve the AI problem.
Knowledge representation:Knowledge Representation is the way of expressing the identified knowledge into some knowledge representation language such as propositional logic, predicate logic etc.
Knowledge manipulation: Large volume of knowledge has no meaning until up to it is processed to deduce the hidden aspects of it. Knowledge is manipulated or knowledge manipulation is done to draw conclusions from knowledgebase.
Learning is concerned with design and development of algorithms that allow computers to evolve behavior based on empirical data such as from sensor data. Learning’s major focus is to automatically learn to recognize complex patterns and make intelligent decision based on data.
A complete program is said to learn from experience E with respect to some class of tasks T and performance measure P, if its performance at tasks in T, as measured by P, improves with experience E.
Intelligent Agents:An Intelligent Agent observes the environment via sensors and acts reasonably upon that environment with its effectors. Thus, an agent gets percepts one at a time, and maps this percept sequence to actions.
Characteristics of the agent
– Interacts with other agents plus the environment
– Reactive to the environment – Pro-active (goal- directed)
What is meant by sensors/percepts and effectors/actions?
– Sensors: Eyes (vision), ears (hearing), skin (touch), tongue (gestation), nose (olfaction), neuromuscular system (proprioception)
– Effectors: limbs, digits, eyes, tongue,
– Actions: lift a finger, turn left, walk, run, and carry an object …
The Point: percepts and actions need to be carefully defined, possibly at different levels of abstraction
Let’s go through a more specific example: Automated taxi driving system:
Compare Software with an agent
Compare Human with an agent
Percept: The Agents perceptual inputs at any given instant.
Percept Sequence: The complete history of everything the agent has ever perceived or observed.
Mathematical concept that maps percept sequence to actions is the Agent Function.
f :P*→ A
Agent Function will internally be represented by the agent program.
The agent program is existent implementation of agent function it runs on the physical architecture to produce f.
The vacuum-cleaner world: Example of an Agent
Environment: square A and B
Percepts: [location and content] E.g. [A, Dirty]
Actions: left, right, suck, and no-op
CSITNEPAL. (n.d.). Retrieved from Csitnepal.com: http://csitnepal.com/elibrary/notes/
Knight., E. R. (n.d.). Artificial Intelligence. In E. R. Knight.. The McGraw-Hill Companies.
Patterson., D. W. (n.d.). Introduction to Artificial Intelligence and Expert Systems. In D. W. Patterson., Introduction to Artificial Intelligence and Expert Systems. Prentice Hall.
slideshare. (n.d.). Retrieved from www.slideshare.net: http://www.slideshare.net/u053675/artificial-intelligence-1419854
Stuart Russell, P. N. (n.d.). Artificial intelligence : a modern approach. In P. N. Stuart Russell, Artificial intelligence : a modern approach. pearson.
tutorialspoint. (n.d.). Retrieved from www.tutorialspoint.com: http://www.tutorialspoint.com/artificial_intelligence/artificial_intelligence_tutorial.pdf
Winston, P. H. (n.d.). Artificial Intelligence. In P. H. Winston, Artificial Intelligence. addison wesley.