Group no.

01 Members: Atif Iqbal Bilal Mehmood Syed Waqar Ahmed Saad Zahoor Talha Salik Asif Choudhry Sabiqa Moazzam Bilawal Iqbal Abdullah Riaz UW-10-ME-BE-001 UW-10-ME-BE-003 UW-10-ME-BE-005 UW-10-ME-BE-009 UW-10-ME-BE-013 UW-10-ME-BE-015 UW-10-ME-BE-017 UW-10-ME-BE-019 UW-10-ME-BE-021

Contents
Definition ....1 Human intelligence ....1 General intelligence factor g .....2 Intelligence testing .....2 Intelligence/emerging issues ..3 Cultural & Racial bias ..3 Uneven child development ...3 Social class bias 3 Gender differences ...3 Theories of intelligence .........3 Cattel-Horn-Carroll theory ..3 Fluid intelligence .4 Crystallized intelligence ..4 Quantitative reasoning .4 Reading & writing ability ....4 Short-term memory .4 Long-term memory ..4 Multiple intelligence .....4 Verbal/linguistic intelligence ..5 Body/kinesthetic intelligence ..5 Musical/rhythmic intelligence .5 Logic/mathematics intelligence ..5 Visual/spatial intelligence ..5
2

Interpersonal relationship ..5 Intrapersonal relationship ..5 Latent inhabitation .5 Evolution of intelligence .....5 Animal and plant intelligence ....5 Artificial intelligence ...6 AIs Origins .....6 Branches of AI ....7 Logical AI ..7 Search .7 Pattern recognition .7 Representation 7 Interference .7 Common sense knowledge & reasoning 8 Learning from experience ..8 Planning ..8 Epistemology ..8 Ontology .8 Heuristics 9 Genetic programming .9 Application of AI..9 Game playing ..9 Speech recognition ..9 Understanding natural language .9
3

Computer vision .9 Expert system ...10 Heuristic classification .10

NATURAL INTELLIGENCE AND ARTIFICIAL INTELLIGENCE

Natural Intelligence:
Definitions:
Intelligence derives from the Latin verb intelligere which derives from inter-legere meaning to "pick out" or discern. A form of this verb, intellectus, became the medieval technical term for understanding, and a translation for the Greek philosophical term nous. To judge well, to comprehend well, to reason well (Binet & Simon 1905) The ability to carry on abstract thinking (Terman 1916) The ability to solve problems or fashion products that are of consequence in a particular cultural setting or community (Gardner 1985) Human Intelligence:
Psychometrics:

The approach to understanding intelligence with the most supporters and published research over the longest period of time is based on psychometric testing. It is also by far the most widely used in practical settings. Intelligence tests are widely used in educational, business, and military settings due to their efficacy in predicting behavior. IQ and g are correlated with many important social outcomesindividuals with low IQs are more likely to be divorced, have a child out of marriage, be incarcerated, and need long-term welfare support, while individuals with high IQs are associated with more years of education, higher status jobs and higher income. Intelligence is significantly correlated with successful training and performance outcomes, and IQ/g is the single best predictor of successful job performance.

General Intelligence Factor Or g:

There are many different kinds of IQ tests using a wide variety of test tasks. Some tests consist of a single type of task, others rely on a broad collection of tasks with different contents (visual-spatial, verbal, numerical) and asking for different cognitive processes (e.g., reasoning, memory, rapid decisions, visual comparisons, spatial imagery, reading, and retrieval of general knowledge). The psychologist Charles Spearman early in the 20th century carried out the first formal factor analysis of correlations between various test tasks. He found a trend for all such tests to correlate positively with each other, which is called a positive manifold. Spearman found that a single common factor explained the positive correlations among test. Spearman named it g for "general intelligence factor". He interpreted it as the core of human intelligence that, to a larger or smaller degree, influences success in all cognitive tasks and thereby creates the positive manifold. This interpretation of g as a common cause of test performance is still dominant in psychometrics. Their mutualism model assumes that intelligence depends on several independent mechanisms, none of which influences performance on all cognitive tests. These mechanisms support each other so that efficient operation of one of them makes efficient operation of the others more likely, thereby creating the positive manifold.

Intelligence Testing: The first Intelligence tests were developed in France by Binet & Simon, in 1905. They were commissioned by the French government to identify children who should attend special schools for the feebleminded to raise their performance. They saw intelligence as a developmental process rather than a fixed entity, i.e. intelligence could be identified in terms of what could normally be expected of a child at a given age, e.g. a 2 year old child could not be expected to recite the days of a week, but an 8 year old child could. By sampling a large number of children, they devised a test that matched a series of tasks to ages in order to determine a childs mental age. Binet and Simon believed that these scores were only a snapshot of how a child was at the moment in time, not something that was fixed for their lives. Scores should only be used to identify children who needed help due to mild retardation or with learning difficulties. They should not be used to rank or label normal children.

Intelligence / Emerging Issues:

Over time, in many countries, parents and educational professionals became concerned about the over reliance on test scores and the labelling of children at such an early age. The following issues of concern emerged:
Cultural And Racial Bias:

There was also increasing awareness that tests were culturally and racially biased and favoured white, middle class individuals. Several Psychologists in America developed tests which claimed to be culture free, but this remains a contentious area of Intelligence.
Uneven Child Development:

The tests penalized children who were described as late developers. Children develop in different ways and at different ages in their early lives. However, many of the children from the Secondary Modern Schools, who showed more rapid development in their early teenage years, were excluded from taking examinations and often left school with few or no formal qualifications. This determined their future careers in factories and low skilled work.
Social Class Bias:

The tests were considered by critics to favour children of the middle classes. There were higher proportions of working class children in the technical and secondary modern schools than in the Grammar schools which had higher proportions of middle class pupils. With hindsight, this testing can be described as a form of labelling and social exclusion.
Gender Differences:

Gender became an issue as girls at the age of 10 / 11 continued to score higher than boys of the same age. To compensate for this in the UK, boys were offered a Grammar School place with a lower 11+ score than girls who, with the same or a higher score, were excluded and sent to the Secondary Moderns or Technical schools.

Theories Of Intelligence:
Cattell-Horn-Carroll Theory:
Many of the broad, recent IQ tests have been greatly influenced by the Cattell-HornCarroll theory. It is argued to reflect much of what is known about intelligence from research. A hierarchy of factors is used. g is at the top. Under it there are 10 broad abilities that in turn are subdivided into 70 narrow abilities. The broad abilities are:
7

Fluid Intelligence: includes the broad ability to reason, form concepts, and solve problems using unfamiliar information or novel procedures. Crystallized Intelligence: includes the breadth and depth of a person's acquired knowledge, the ability to communicate, and the ability to reason using previously learned experiences or procedures. Quantitative Reasoning: the ability to comprehend quantitative concepts and relationships and to manipulate numerical symbols. Reading & Writing Ability: includes basic reading and writing skills. Short-Term Memory: is the ability to apprehend and hold information in immediate awareness and then use it within a few seconds. Long-Term Memory: is the ability to store information and fluently retrieve it later in the process of thinking.

Multiple Intelligences:
Howard Gardner (1985) developed the Theory of Multiple Intelligences as a challenge to the earlier views of intelligence which predominated up to the 1970s which can be summarized as:
Intelligence is a single entity We are born with a certain amount of intelligence (nature) It is difficult to alter this amount by environmental influences (nurture) IQ can be measured by a test

Gardner developed his theory of Multiple Intelligences over nearly four decades through his work with individuals from a wide age and ability range. He worked with people with specific learning difficulties and brain injuries, prodigies and autistic individuals. From these unusual populations, he came to see intelligence as a set of multidisciplinary abilities. Gardner described intelligence as: The ability to solve problems or fashion products that are of consequence in a particular cultural setting or community (Gardner1993) Gardner originally identified 7 then 8 intelligences:

Verbal/linguistic:

For example: Lexical skills, formal speech, verbal debate, creative writing
Body/Kinesthetic: (movement)

For example: Body language, physical gestures, creative dance, physical exercise, drama
Musical/Rhythmic:

For example: Music performance, singing, musical composition, rhythmic patterns

Logic/Mathematic:

For example: Numerical aptitude, problem solving, deciphering codes, abstract symbols and formulas
Visual/Spatial:

For example: Patterns and designs, painting, drawing, active imagination, sculpture
Interpersonal:(relationships with others)

For example: Person-to-person communication, empathy practices, group projects, collaboration skills, receiving and giving feedback
Intrapersonal:(self-understanding and insight)

For example: Thinking strategies, emotional processing, knowing yourself, higher order reasoning, focusing/concentration.

Latent inhibition:
Latent inhibition has been related to elements of intelligence, namely creativity and genius.

Evolution of intelligence:
The ancestors of modern humans evolved large and complex brains exhibiting an ever-increasing intelligence through a long evolutionary process (see Homininae). Different explanations have been proposed.

Animal and plant intelligence:

Although humans have been the primary focus of intelligence researchers, scientists have also attempted to investigate animal intelligence, or more broadly, animal cognition. These researchers are interested in studying both mental ability in a particular species, and comparing abilities between species. Nonhuman animals particularly noted and studied for their intelligence include chimpanzees, bonobos (notably the language-using Kanzi) and other great apes, dolphins,

elephants and to some extent parrots, rats and ravens. Controversy exists over the extent to which these judgments of intelligence are accurate.

Artificial intelligence (AI):Artificial Intelligence (AI) is an advance branch of science that studies the process of human thinking and attempts to apply the knowledge to simulate the same process in machines. Artificial intelligence (AI) is the intelligence of machines and the branch of computer science that aims to create it. AI textbooks define the field as "the study and design of intelligent agents" where an intelligent agent is a system that perceives its environment and takes actions that maximize its chances of success. John McCarthy, who coined the term in 1956, defines it as "the science and engineering of making intelligent machines." As computers are far ahead in the marathon of processing machines, AI is considered to be the branch of Computer Science than that of General Science. There have been many research and development in the field of Artificial Intelligence. The area of research include speech and pattern recognition, natural language processing, learning from previous experiences (learning by making and correcting mistakes!), reasoning under the situations providing limited or incomplete information etc. AI is practically applied in the field of computer games, expert systems, neural networks, robotics and many other fields of science and technology.

AIs Origins:
The history of artificial intelligence began in antiquity, with myths, stories and rumors of artificial beings endowed with intelligence or consciousness by master craftsmen; as Pamela McCorduck writes, AI began with "an ancient wish to forge the gods."[1] The origins of Artificial Intelligence (AI) usually incorporate the theories and thoughts proclaimed by several ancient Greek philosophers and scientists. Although, arguments can be made that the Egyptians originally garnered that stake with the advancements they made around 800 B.C. In the ancient Egyptian city of Napata, a statue of the great Amun was constructed to move its arm up and down and to speak to onlookers as well. Even though the statue was not actually intelligent, it did have an impact on the Egyptians at the time of being able to portray intelligence. The first concrete advancement of artificial intelligence was derived by Aristotle in the 5th century. This theory is known as syllogistic logic, the first formal deductive reasoning system. Others followed, such as Euclids Elements, which was a 13 book
10

collection based on a formal model of reasoning, geometry, and number theory. Muslim scientist al-Khwrizm coined the acceptance of algebra and the term algorithm. In the 13th Century, Ramon Lull invented the Zairja, a machine which attempted to generate ideas in a non-mathematical, mechanical format. In the 15th Century, the first modern measuring machine was invented, the clock.

Branches of AI:
Here's a list, but some branches are surely missing, because no-one has identified them yet. Some of these may be regarded as concepts or topics rather than full branches.
Logical AI:

What a program knows about the world in general the facts of the specific situation in which it must act, and its goals are all represented by sentences of some mathematical logical language. The program decides what to do by inferring that certain actions are appropriate for achieving its goals. The first article proposing this was [McC59]. [McC89] is a more recent summary. [McC96b] lists some of the concepts involved in logical AI. [Sha97] is an important text.
Search:

AI programs often examine large numbers of possibilities, e.g. moves in a chess game or inferences by a theorem proving program. Discoveries are continually made about how to do this more efficiently in various domains.
Pattern recognition:

When a program makes observations of some kind, it is often programmed to compare what it sees with a pattern. For example, a vision program may try to match a pattern of eyes and a nose in a scene in order to find a face. More complex patterns, e.g. in a natural language text, in a chess position, or in the history of some event are also studied. These more complex patterns require quite different methods than do the simple patterns that have been studied the most.
Representation:

Facts about the world have to be represented in some way. Usually languages of mathematical logic are used.
Inference:

From some facts, others can be inferred. Mathematical logical deduction is adequate for some purposes, but new methods of non-monotonic inference have been
11

added to logic since the 1970s. The simplest kind of non-monotonic reasoning is default reasoning in which a conclusion is to be inferred by default, but the conclusion can be withdrawn if there is evidence to the contrary. For example, when we hear of a bird, we man infer that it can fly, but this conclusion can be reversed when we hear that it is a penguin. It is the possibility that a conclusion may have to be withdrawn that constitutes the non-monotonic character of the reasoning. Ordinary logical reasoning is monotonic in that the set of conclusions that can the drawn from a set of premises is a monotonic increasing function of the premises. Circumscription is another form of non-monotonic reasoning.
Common sense knowledge and reasoning:

This is the area in which AI is farthest from human-level, in spite of the fact that it has been an active research area since the 1950s. While there has been considerable progress, e.g. in developing systems of non-monotonic reasoning and theories of action, yet more new ideas are needed. The Cyc system contains a large but spotty collection of common sense facts.
Learning from experience:

Programs do that. The approaches to AI based on connectionism and neural nets specialize in that. There is also learning of laws expressed in logic. [Mit97] is a comprehensive undergraduate text on machine learning. Programs can only learn what facts or behaviors their formalisms can represent, and unfortunately learning systems are almost all based on very limited abilities to represent information.
Planning:

Planning programs start with general facts about the world (especially facts about the effects of actions), facts about the particular situation and a statement of a goal. From these, they generate a strategy for achieving the goal. In the most common cases, the strategy is just a sequence of actions.
Epistemology:

This is a study of the kinds of knowledge that are required for solving problems in the world.
Ontology:

Ontology is the study of the kinds of things that exist. In AI, the programs and sentences deal with various kinds of objects, and we study what these kinds are and what their basic properties are. Emphasis on ontology begins in the 1990s.

12

Heuristics:

A heuristic is a way of trying to discover something or an idea imbedded in a program. The term is used variously in AI. Heuristic functions are used in some approaches to search to measure how far a node in a search tree seems to be from a goal. Heuristic predicates that compare two nodes in a search tree to see if one is better than the other, i.e. constitutes an advance toward the goal, may be more useful. [My opinion].
Genetic programming:

Genetic programming is a technique for getting programs to solve a task by mating random Lisp programs and selecting fittest in millions of generations. It is being developed by John Koza's group and here's a tutorial.

Applications of AI:
Here are some applications of AI,
Game playing:

You can buy machines that can play master level chess for a few hundred dollars. There is some AI in them, but they play well against people mainly through brute force computation--looking at hundreds of thousands of positions. To beat a world champion by brute force and known reliable heuristics requires being able to look at 200 million positions per second.
Speech recognition:

In the 1990s, computer speech recognition reached a practical level for limited purposes. Thus United Airlines has replaced its keyboard tree for flight information by a system using speech recognition of flight numbers and city names. It is quite convenient. On the the other hand, while it is possible to instruct some computers using speech, most users have gone back to the keyboard and the mouse as still more convenient.
Understanding natural language:

Just getting a sequence of words into a computer is not enough. Parsing sentences is not enough either. The computer has to be provided with an understanding of the domain the text is about, and this is presently possible only for very limited domains.
Computer vision:

The world is composed of three-dimensional objects, but the inputs to the human eye and computers' TV cameras are two dimensional. Some useful programs can work solely in two dimensions, but full computer vision requires partial three-dimensional information that is not just a set of two-dimensional views. At present there are only
13

limited ways of representing three-dimensional information directly, and they are not as good as what humans evidently use.
Expert systems:

A ``knowledge engineer'' interviews experts in a certain domain and tries to embody their knowledge in a computer program for carrying out some task. How well this works depends on whether the intellectual mechanisms required for the task are within the present state of AI. When this turned out not to be so, there were many disappointing results. One of the first expert systems was MYCIN in 1974, which diagnosed bacterial infections of the blood and suggested treatments. It did better than medical students or practicing doctors, provided its limitations were observed. Namely, its ontology included bacteria, symptoms, and treatments and did not include patients, doctors, hospitals, death, recovery, and events occurring in time. Its interactions depended on a single patient being considered. Since the experts consulted by the knowledge engineers knew about patients, doctors, death, recovery, etc., it is clear that the knowledge engineers forced what the experts told them into a predetermined framework. In the present state of AI, this has to be true. The usefulness of current expert systems depends on their users having common sense.
Heuristic classification:

One of the most feasible kinds of expert system given the present knowledge of AI is to put some information in one of a fixed set of categories using several sources of information. An example is advising whether to accept a proposed credit card purchase. Information is available about the owner of the credit card, his record of payment and also about the item he is buying and about the establishment from which he is buying it (e.g., about whether there have been previous credit card frauds at this establishment).

14