Artificial Intelligence
Content
Written by : Wateen Abdullah al-iady Class code : C6
Submission date : Subject : Artificial Intelligence (AI)
1
Table Content :
i. ii. abstract introduction
1. The definition of Artificial intelligence...................................................... 3 2. A brief history on AI «««««««««««.««««««..3 3. The two main categories of Intelligent Agent ««««..««.3 4. The aim of AI ««««««««««««««««««««..4 5. Methods used in AI ««««««««««««««.««««4 5.1 Semantic Networks««««««««««««..«««««.5 5.2 Frames«««««««««««««««««««««..««««..5 5.3 Decision trees«««««««««««««««««««««««.5 5.4 Predicate logic««««««««««««««««....««««««6 5.5 Neural networks««««««««««««««««««««««6 6. Developments on AI (Expert system )«««««««««.«««..«.7 7. Perception( understanding using senses )««««««««..«..««.8 7.1 Visual recognition «...««««««««««««..««.««..««8 7.1 Audio understanding ««««««««««««««..««.«««9 8. Applications on AI «««««««««««««««««...««««9 9. conclusion 10. references 11. Terms
2
1.
Artificial Intelligence Introduction
artificial intelligence is an important achievement in the development of computer science. which has a wide range of applications in many areas . This field is extraordinarily difficult to encapsulate either chronologically or thematically . the reason for this is that there has never been a groundswell of effort leading to a recognized achievement. So this research, paper will discuss some topics in this field. This , research discusses the following : The definition and the essence of AI in section 1 , Although the concept of AI was mentioned in the past but AI is approximately a new field of technologies because applications on this fields have started before a short time ( around 60 years ) from now . Artificial intelligence is not a human intelligence, and no more than human intelligen ce . The paper displays a brief history of (AI) in section 2 , and sums up the history and present situation of artificial intelligence . The first time AI concept was mentioned and the first time it became a reality . The paper divides the intelligent agent in to its Two main categories in section 3 , A machine who acts and behaves in a smart way needs to have a system that provides this to them . Software agent is the system if it was applied to a machine or device that moves and acts a Physical agent will be produced . The paper shows the aim and the goal of AI in section 4, and how it can make a huge difference in life . The ability of machines to perform difficult tasks instead of humans . Also ,The paper defines some of the Methods used in AI in section 5 . Semantic networks , Frames ,decision trees , Predicate Logic , neural networks are some of the methods that the paper will have . Furthermore , The paper also analyzes its development direction ,mainly discusses the development trends in two fields of artificial intelligence, such as, expert systems and Visual and audio recognition and understanding in section 6 .
3
Finally it will conclude with AI applications and its future studies in section 7 . Artificial intelligence has been deep into the social life in all fields; it has been and will continue to be inevitably changing our lives .
Artificial intelligence (AI) : 1.
Artificial Intelligence , the English abbreviation is AI . It is a new technological science . it attempts to understand the substance of intelligence, and produce a new intelligent machine could make reactions similar to the human intelligence, the research on the field of artificial intelligence include robot ,speec h recognition, image recognition , natural language processing and expert system . AL 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 . Artificial intelligence, by its essence, is the simulation of the information process of human thinking. There is two roads in stimulation th e first is structure simulation and the second is functional simulation . but still Artificial intelligence is not a human intelligence, and no more than human intelligence. Research scientists in Artificial Intelligence try to get machines to exhibit behavior that is called intelligent behavior that is observed in human beings .Some of behaviors are obstructive which scientists do not yet know how to solve them properly by computers .Machines require a certain system that is able to make them behave smartly which is called Intelligent agent.
A brief History of ( AI): 2.
Although AI is a new field of study it has roots in the past . The field of AI is generally held to have started at a conference in July 1956 at Dartmouth College when the phrase ´Artificial Intelligenceµ was first used. It was attended by many of those who became leaders in the field including John McCarthy, Marvin Minsky, Oliver Selfridge, Ray Solomonoff, Trenchard More, Claude Shannon, Nathan Rochester, Arthur Samuel, Allen Newell, and Herbert Simon . The roots of AI, may be found in Greek mythology .The concept of logical reasoning was i nvented by a Greek philosopher. Intelligent artifacts appear in literature since then, with real (and fraudulent) mechanical devic es actually made to behave with some degree of intelligence . An examples of a real mechanical device that behaves smartly printers , and modern clocks .In the 15th century printing was invented by a moving type . With the passage of days between the 15 th and the 16 th century clocks ,the first modern measuring machines were produced using lathes . After modern computers became available, following World War II ,the concept of thinking machines were firstly thought by Alan Turing , who proposed the Turing test which provides a definition of intelligence in a machine by comparing the intelligent behavior of a machine with that of the human . it has become possible to create programs that
4
perform difficult intellectual tasks. From these programs, general tools a re constructed which have applications in a wide variety of everyday problems , An example for this a robot was made in the late of 1990`s with auditory , visual and expressive system in human social interaction and to demonstrate simulated human emotion and appearance .The name Kismet comes from the Arabic, Turkish, Urdu, Hindi and Punjabi word meaning "fate" or sometimes "luck".
3. Two main categories for Intelligent agent :
Its divided into two broad categories : Software agent such as search engine used to search world wide web and find sites can provide information about requested subject , and the Physical agent (Robot) that can do tasks instead of human such as : painting . collecting , etc . Mobile robots are robots used in organizations to perform delivery tasks or prospect oil underwater .They have the capability to move around in their environment and are not fixed to one physical location. In contrast, industrial robots can't work as efficient as mobile robots . Mobile robots are the focus of a great deal of current research and almost every major university has one or more labs that focus on mobile robot research . Mobile robots are also found in industry, military and security environments. They also appear as consumer products, for entertainment or to perform certain tasks like vacuum. Furthermore , there is A humanoid robots which is an autonomous Mobile robots . There is still a lot of work before such robots can learn interact properly with the surroundings . intelligent software has a wide range of programmable languages that creates it but Two languages are specifically d esigned for AI : LISP and PROLOG.
4 .The aim of artificial intelligence :
The goal of work in artificial intelligence is to build machines that perform tasks normally are done by human intelligence like: to make systems that can work as experts . Also, to create a machine that behaves like human -To understand their surroundings through senses : sight , hearing , smell , taste. Scientists discovered how to make machines have the sight and hearing ability . They may discover in the future a robots that have all senses . Provide machines that can work instead of humans in Cumbersome tasks such as : welding , assembling , vacuuming « etc.
5. Methods used in (AI)-software agent- :
Artificial agent needs to be able to represent k nowledge so it can solve some problems related to the real world .Facts are represented in the computer or the smart machine as a data structure and its being manipulated by programs inside the computer .There is a lot of methods for representing facts . 1-A semantic network or net is one of the representation methods which is a graphic notation for representing knowledge in patterns of interconnected nodes and arrows (arcs) . Computer implementations of semantic networks were first
5
developed for artificial intelligence and machine translation . It uses Concepts (nodes)to represent the object and edges(arcs) to represent the relation between the two concepts .For example livings (super class ) a concept , we connect this concept to one of its( subclass es )humans by a relation ²an arrow- , which we can also connect it with one of the examples Peter ( Instance ) is Male . A Concept is divided to sets ²from the previous example : livings humans Peter .The relation could define an attribute of the concept such as : ( color , size , length « ). 2-Frame is other method which uses records to represent knowledge . The method uses a set of frames each frame has a concept and its definition either it was a super class or a sub class .Programs can handle frames more easily than semantic networks. It uses slots to represent the relation and objects . 3-Also , decision trees one of the methods used. It is a classifier in the form of a tree structure. It separates data into subsets and then analyses them into further subsets, and so on for few sublevels .The final subsets are precise. We Use a decision tree to predict categories for new events . Each decision node is labeled with an attribute. , each arc is labeled with a value for the nodes attribute, and each leaf node is labeled with a category .
Semantic nets are easily converted into decision trees, with the nodes representing goals and the links representing decisions that result from attaini ng one goal, and that lead to another goal
4-Furthermore , Predicate logic is other method to represent knowledge . Predicate logic, involves using standard forms of logical symbolism which have been familiar to philosophers and mathematicians for many decades . It can be represented in terms of logical formulae in which a predicate is applied to one or more arguments. Preposional logic is simpler language which uses five operators (NOT ),(OR),(AND),(IF« THEN ), and (IF AND ONLY IF ). Consider the following sentence: ``Every respectable villager worships God .'' A moment's reflection will reveal that this is ambiguous. Is it saying that there is one single God to which each respectable villager offers worship? Or does each worshipper have his or her own God, to which a fellow respectable villager may or may not be also praying? With predicate logic it is easy to reveal the nature of the ambiguity, by a device known as quantification . We can now use quantification to exhibit the ambiguity .Two quantifiers are common in predicate logic " For all " and " there exist ". 5-Neural networks : It is one of the methods used in machines in order to help it 'learn like humans . It is a parallel system, capable of resolving models that linear computing cannot. It is one of the newest signal-processing technologies. It`s system operates by simulating the operation of biological neural networks, in other words ,it`s system is based on the operation of biological neural system. Why would be necessary the imitation of artificial neural networks? Although computing these days is truly advanced, there are certain tasks that a program made for a common microprocessor is unable to perform; even so a software i mitation of a neural network can be made with their advantages and disadvantages .When creating a functional model of the biological neuron, there ar e three basic components of perceptrons . First, the synapses of the neuron are modeled as weights. The strength of the connection between an input and a neuron is noted by the value of
6
the weight. Negative weight values reflect inhibitory connections, whi le positive values designate excitatory .The next two components model the actual activity within the neuron cell. An adder sums up all the inputs modified by their respective weights. This activity is referred to as linear combination. Finally, an activat ion function controls the amplitude of the output of the neuron. The Computation in An Artificial Neural Network was designed to be adaptive, most often nonlinear (parallel) system that learns to perform a function from data. Adaptive means that the system can change itself in response to changes in its environment in such a way (21), normally called the training phase . After the training phase the Artificial Neural Network parameters are fixed and the system is deployed to solve the problem at hand (the testing phase ). The Artificial Neural Network is built with a systematic step-by-step procedure to optimize a performance criterion or to follow some implicit learning rules . The input/output training data are fundamental in neural network technology, because they convey the necessary information to "discover" the optimal operating point. The nonlinear nature of the neural network processing elements provides the system with lots of flexibility to achieve practical ly any desired input/output map. An input is presented to the neural network and a corresponding desired or target response set at the output (when this is the case the training is called supervised ). An error is composed from the difference between the desired response and the system output. This error information is fed back to the system and adjusts the system parameters in a systematic fashion (the learning rule). The process is repeated until the performance is acceptable. .They can be used in (OCR) optical character recognition , which intell igent agent is supposed to read any handwritings.
6. The development trends in AI : Expert systems :
Is an example of software programs that is based on software intelligent agents . They work instead of expert people . A wide variety of methods can be used to simulate the performance of the expert; however, common to most or all are : 1) the creation of a knowledge base which uses some knowledge representation structure to capture the knowledge of the Subject Matter Expert 2) a process of gathering that knowledge from the SME and codifying it according to the structure, which is called knowledge engineering and 3) once the system is developed, it is placed in the same real world problem solving situation as the human SME, typically as an aid to human workers or as a supplement to some information system. An example is medical expert system it is used to diagnose illnesses , to give the right treatments to illness , and tasks are normally made by a doctor .It is build on predefined knowedge about a certain field of expertise .A knowledge engineer build the expert system , who may not be an expert in the field , because he has expertise to know how to do the interview and how to interpret the answers so that can be used in building the knowledge . Some problems of uncertainty may occur due the following : a human, when reasoning, does not always make statements with 100% confidence for example "If reptile is green, then he is probably a frog" (after all, he might be a chameleon). so The MYCIN rule based expert system introduced a quasi-probabilistic approach called certainty factors . This type of reasoning can be imitated using numeric values called
7
confidences . For the previous example it is known that reptile is green, it might be concluded with 0.85 confidence that he is a frog; or, if it is known that he is a frog, it might be concluded with 0.95 confidence that he hops. These certainty factor (CF) numbers quantify uncertainty in the degree to which the available evidence supports a hypothesis. As each new piece of evidence becomes available an increases and decreases of CF is associated with a hypothesis . but builders must ensure that the system will give its users accurate advice or correct solutions to their problems .It can include seven components : User , User interface , Inference engine , knowledge base , fact database , explanation system , and knowledge base editor .Inference engine is the heart of an expert system : it communicates with the knowledge base , fact base , and the user interface . Explanation system, and knowledge base editor may not be included in some expert systems .
Perception ( image and language recognition and understanding ): Visual Recognition :
computer vision the science and technology of machines that see, where see in this case means that the machine is able to extract information from an image that is necessary to solve some tasks . Computer vision is concerned with the theory behind artificial systems that extract information from images. The image data can take many forms .It is used in many applications such as : interacting with humans . Computer vision is closely related to the study of biological vision. The field of biological vision studies and models the physiological processes behind visual perception in humans and other animals. Computer vision, on the other hand, studies and describes the processes implemented in software and hardware behind artificial vision systems. Interdisciplinary exchange between biological and computer vision has proven fruitfu l for both fields. Its relatively new field of study. In the early days of computing, it was difficult to process even moderately large sets of image data. It was not until the late 1970s that a more focused study of the field emerged. Computer vision covers a wide range of topics which are often related to other disciplines, and consequently there is no standard formulation of "the computer vision problem". Moreover, there is no standard formulation of how computer vision problems should be solved. Instead , there exists an abundance of methods for solving various well -defined computer vision tasks, where the methods often are very task specific and seldom can be generalized over a wide range of applications. Many of the methods and applications are still in the state of basic research , but more and more methods have found their way into commercial products, where they often constitute a part of a larger system which can solve complex tasks (e.g., in the area of medical images, or quality control and measure ments in industrial processes). In most practical computer vision applications, the computers are pre programmed to solve a particular task, but methods based on learning are now becoming increasingly common . Although it is an easy job for human to use their eyes , it turns out to be a hard task for an Artificial agent . How image is being processed ? It goes
8
through different steps . Edge detection is the first step in processing images .Edges can define boundaries between the object and its background .It indicates the contrast between the surfaces of the object and its background .It can find the boundaries between the object and its environment by using the intensity of the pixels . When a great deference of the pixels intensities is found ,there it will detect the edge . Segmentation is the second step is of image analysis .It divides the image into homogenous segments or areas .This step is similar to edge detection but the differences is that the edge detection finds the boundaries between the object and its background ,in segmentation boundaries between different areas inside the object are found . After this step is finished the object is divided into different areas .After that , the third step finding the depth of the object or objects in the image . Depth finding can help intelligent agent to gauge how far the object is from it .Two general methods are used for this purpose stereo vision and motion . a. Stereo vision uses one of the technique developed by human eyes to find the depth of the object . To have good distance recognition a hum needs two eyes . If the object is very close , two images created in your eyes are different , but if the object is far away the images are almost the same . So one of the tools use d in this method is to use to eyes or two cameras .The other method is called b .Motion it is based on taking several images to tell give clue to the distance of objects . For example , assume that the video shows a person moving towards a house . the distance between the person and the house ( close object ) will change but the distance between the person and a mountain will remain the same . Finding orientation is the forth step in analyzing images . One of techniques used is shading . Shading is based on the amount of light reflected from a surface that depends on the orientation of the su rface ( its position ) . Finally object recognition but to recognize an object it needs to have a model of the object in the memory . So it assume that the object is a compound of objects made of simple geometric shapes . Those shapes are stored in the memory .
Audio understanding :
A machine that can understand natural language can be really useful in our daily life . For example , it can replace a telephone operator . We can dived the task of machine that understands natural language into four consecutive steps : The first step is speech recognition .After the speech has been recognized the next step is syntactic analysis where the system defines where the word are to be grouped in the sentence . Why It·s a complex task ? For example John gave Sara the book = Sara was given the book by john . The system needs to interpret both sentences correctly and come with same conclusion . The third step is semantic analysis where it extracts the meaning of the sentence . In this step analysis cr eates a representation of the objects involved in the sentence , their relation , and their attributes . The last step is pragmatic analysis .This last step is needed to further clarify and to remove ambiguities .The machine has to understand the purpose of the sentence in order to act among understanding it .It has to make difference between requesting , promising , inquiring , and so on . Pragmatic analysis is required to find the purpose of the sentence . Sometimes a sentence is ambiguous after semantic analysis .Ambiguity can manifest itself in different ways . A word can have more than one function for example , the word hard can be both adjective or
9
a adverb . A word can have more than one meaning For example the word " ball " can have different meanings " football " or " ball room " .Also words with the same pronunciation can have different spelling and meaning .
Applications on AI :
Artificial intelligence has been used in a wide range of fields including medical diagnosis , stock trading , robot control , law, scientific discovery and toys . However, many AI applications are not perceived as AI : " A lot of cutting edge AI has filtered into general applications, often without being called AI because once something becomes useful enough and common enough it's not labeled AI anymore." . " Many thousands of AI applications are deeply embedded in the infrastructure of every industry ." In the late 90s and early 21st century, AI technology became widely used as elements of larger systems, but the field is rarely credited for these successes . Banks use artificial intelligence systems to organize operations , invest in stocks , and manage properties . In August 2001 , robots beat humans in a simulated financial trading competition . Financial institutions have long used artificial neural network systems to detect charges or claims outside of the norm , flagging these for human investigation . A medical clinic can use artificial intelligence systems to organize bed schedules , make a staff rotation , and provide medical information . Artificial neural networks are used for medical diagnosis. Robots have become common in many industries. They are often given jobs that are considered dangerous to humans. Robots have proven effective in jobs that are very repetitive which may lead to mistakes or accidents due to a lapse in concentration and other jobs which humans may find degrading. General Motors Corporation uses around 16,000 robots for tasks such as painting, welding, and assembly. Japan is the leader in using and producing robots in the world. In 1995, 700,000 robots were in use worldwide; over 500,000 of which were from Japan. AI has also been applied to video games . Various tools of artificial intelligence are also being widely deployed in homeland security, speech and text recognition, data mining, and e-mail spam filtering . Applications are also being developed for gesture recognition (understand ing of sign language by machines), individual voice recognition (, global voice recognition (from a variety of people in a noisy room), facial expression recognition. AL is used in medical computer vision or medical image processing. This area is characte rized by the extraction of information from image data for the purpose of making a medical diagnosis of a patient. This application area also supports medical research by providing new information, e.g., about the structure of the brain, or about the quali ty of medical treatments. Military applications are probably one of the largest areas for computer vision. The obvious examples are detection of enemy soldiers or vehicles and missile guidance . A second application area in computer vision is in industry, sometimes called machine vision, where information is extracted for the purpose of supporting a manufacturing process. One example is quality control where details or final products are being automatically inspected in order to find defects One of the newer application areas is autonomous vehicles, which include submersibles, landbased vehicles (small robots with wheels, cars or trucks), aerial vehicles, and unmanned aerial vehicles . The level of autonomy ranges from fully autonomous (unmanned) vehicles to vehicles where computer vision based systems support a driver or a pilot in various situations . Space exploration is already being made with
10
autonomous vehicles using computer vision, e. g., NASA's Mars Exploration Rover and ESA's Exo Mars Rover . Needless to say, the reality of today's AI technology is not even close to achieving the far-reaching visions of sci-fi. But could scientists one day - albeit at some distant far off point - create an artificial general intelligence (AGI), a machine that possesses human-level smarts? "Ultimately I think so," Daphne Koller, a professor in the Stanford AI Lab at the Computer Science Department of Stanford University in California, tells silicon.com. "Yes, I think ultimately it is possible. Ultimately, we will get machine learning technology to the point where the machine can adapt itself sufficiently that it's actually learning from lifelong experience, and in all realms, and I think that would eventually drive us towards that goal but it's going to take a very, very, very, very long time."
11
Terms used in the essay (AI) :
1-Ai (Artificial intelligence ) : is a study of programmed systems that can simulate , to some extent , human activities such as perceiving , thinking , learning , and acting . 2-Turing test :It¶s a test that compares the intelligent behavior of a human being with that of a computer by an interrogator . 3-Intelligent agent : A system that perceives its environment , learn from it , and interact with it intelligently . 4-Software agent : A set of programs that are designed to do particular tasks .such as classifying . 5-Physical agent (Robot ) : Is a programmable system that can be used to perform a variety of tasks .such as : painting , welding . 6- mobile robot : is an automatic machine that is capable of movement in a given environment . 7- humanoid robots : which is an autonomous Mobile robots . Robots that can behave like humans 8- industrial robots : usually consist of a jointed arm (multi-linked manipulator) and gripper assembly (or end effectors) that is attached to a fixed surface.
10 - Semantic networks :A directed graphs to represent knowledge . a-Concept = Vertices =Node( It can be thought of as a set or subset or a member ). b-Relations =Edges ( Arrows used to represent the relation between two concepts ).
12
11-Frames : A data structure ( records ) are used to represent knowledge . a-Object : ( It can be thought of as a set or subset or a member ). b-Slots : ( Fields in the data structure ).
NOTICE : We use the vocabulary Node in Semantic networks , and object in the Frames. AND Edges in Semantic networks , Slots in the Frames . 12- decision trees : It is a classifier in the form of a tree structure. It separates data into subsets and then analyses them into further subsets, and so on for few sublevels.
a- decision node: b- leaf node:
12- Predicate logic : A well-defined language developed via a long history of theoretical logic to represent complex facts . 13 - arguments is similar to, but not identical with
14- Propositional logic : A simpler language that is made up from a set of sentences that can be used to carry out reasoning about the world .
15- Quantification allows one to talk in a general way about all things of a certain class or about some particular but unspecified thing of a certain class
16- neural networks : It is one of the newest signal-processing technologies. It`s system operates by simulating the operation of biological neural networks.
17- perceptrons : is an artificial neuron to a single biological neuron . 16 -expert system : it performs tasks that normally needs a human expertise. 17- User interface : allows the user to interact with the system .The system accepts natural language. 18- inference engine : Is the heart of the system that uses the knowledge base and fact data base to infer the action to be taken . 19-Knowledge base : Is a collection of knowledge based on interview with experts in the relevant field of expertise .
13
20- fact database: :It is an case-based .For each case , the user inters the available or measured data into the fact database to be used by inference engine for that particular case 21- Explanation system : It is used to explain the rationale behind the decision made by the inference engine . 22-Knowledge editor : It is used to update the knowledge base if knew experiences has been obtained from experts in this filed . 23- perception : to understand receiving through sensing . 24-Edge detection : finding where the edges in the image are. 25- Segmentation : divides the image into homogenous areas . 26- homogenous segments : The intensity of pixals in these areas are almost the same . 27- Depth finding can help intelligent agent to gauge how far the object is from it. . a. Stereo vision uses one of the technique developed by human eyes to find the depth of the object
b-Motion it is based on taking several images to tell give clue to the distance of objects to determine how far are objects .
28- Finding orientation is the forth step in analyzing images . the aim of it to find the orentiation of an object . 28.1- . Shading is based on the amount of light reflected from a surface that shows the orientation of the surface ( its position ) . 29. speech recognition: The first stop in audio recognition process that divides the speech into words . 30. syntactic analysis : The second step in audio processing where the system defines where the word are to be grouped in the sentence 31. semantic analysis : The third step in audio recognition process where it extracts the meaning of the sentence. 32. pragmatic analysis .This last in audio recognition where is needed to further clarify and to remove ambiguities.
14
References :
In section 1 I used the following : y ^ Poole, Mackworth & Goebel 1998 , p. 1 (who use the term "computational intelligence" as a synony m for artificial intelligence). Other textbooks that define AI this way include Nilsson (1998), and Russell & Norvig (2003) (who prefer the term "rational agent") and write "The whole -agent view is now widely accepted in the field" ( Russell & Norvig 2003, p. 55) These textbooks are the most widely used in academic AI. See Textbooks at AI topics ^ This definition, in terms of goals, actions, perception and environment, is due to Russell & Norvig (2003). Other definitions also include knowledge and learning as additional criteria.
y
In section 2 : . Buchanan, Bruce G. A (Very) Brief History of Artificial Intelligence. AI mentioned reference .
. J. McCarthy, M. L. Minsky, N. Rochester, and C. E. Shannon, "A
Magazine 26(4):
Winter 2005, 53²60 * which I found in a website that used the
proposal for the Darthmouth summer research project on artificial intelligence", available at http://wwwformal.stanford.edu/jmc/history/dartmouth/dartmouth.html, August 31 1955.
15
. Bruce Buchanan and John McCarthy at the AI TOPICS booth at AAAI-02 in Edmonton, Canada (August 2002 available at http://www.aaai.org/AITopics/pmwiki/pm wiki.php/AITopics/BriefHistory
.
M. Turing, "Computing machinery and intelligence", Mind , vol. 59,
pp. 433-460,
http://www.ai.mit.edu/projects/sociable/baby -bits.html . . ^ a b c Peter Menzel and Faith D'Aluisio. Robosapiens. Cambridge: The MIT Press, 2000. Pg. 66 available in http://en.wikipedia.org/wiki/Kismet_(robot) In section 3 :. y y http://en.wikipedia.org/wiki/Mobile_robot foundation of computer science , behrouz forouzan and firouz mosharraf p.g.467 http://www.cengage.co.uk/forouzan/
IN section 5 : y y y y y )-foundation of computer science , behrouz forouzan and firouz mosharraf p.g.490 http://www.cengage.co.uk/forouzan/ oxford english for information technology ,Eric H. Glendinning , John McEwan p.g.22 http://www.cs.bham.ac.uk/research/projects/poplog/computers and thought/chap3/node6.html http://www.learnartificialneuralnetworks.com/ http://www.answers.com/topic/adaptive -system
In section 6: y http://en.wikipedia.org/wiki/Expert_system
In section 7: y y Computer Vision Online A good source for source codes, software packages, datasets, etc. related to computer vision foundation of computer science page 480 .second edition .
In section 8 :
16
y
y
Russell, Stuart J.; Norvig, Peter (2003), Artificial Intelligence: A Modern Approach (2nd ed.), Upper Saddle River, New Jersey: Prentice Hall, ISBN 0-13-790395-2, http://aima.cs.berkeley.edu/ Kurtzweil, Ray (2005), The singularity is near : when humans transcend biology, New York: Viking, ISBN 9780670033843
17
Submission date : Subject : Artificial Intelligence (AI)
1
Table Content :
i. ii. abstract introduction
1. The definition of Artificial intelligence...................................................... 3 2. A brief history on AI «««««««««««.««««««..3 3. The two main categories of Intelligent Agent ««««..««.3 4. The aim of AI ««««««««««««««««««««..4 5. Methods used in AI ««««««««««««««.««««4 5.1 Semantic Networks««««««««««««..«««««.5 5.2 Frames«««««««««««««««««««««..««««..5 5.3 Decision trees«««««««««««««««««««««««.5 5.4 Predicate logic««««««««««««««««....««««««6 5.5 Neural networks««««««««««««««««««««««6 6. Developments on AI (Expert system )«««««««««.«««..«.7 7. Perception( understanding using senses )««««««««..«..««.8 7.1 Visual recognition «...««««««««««««..««.««..««8 7.1 Audio understanding ««««««««««««««..««.«««9 8. Applications on AI «««««««««««««««««...««««9 9. conclusion 10. references 11. Terms
2
1.
Artificial Intelligence Introduction
artificial intelligence is an important achievement in the development of computer science. which has a wide range of applications in many areas . This field is extraordinarily difficult to encapsulate either chronologically or thematically . the reason for this is that there has never been a groundswell of effort leading to a recognized achievement. So this research, paper will discuss some topics in this field. This , research discusses the following : The definition and the essence of AI in section 1 , Although the concept of AI was mentioned in the past but AI is approximately a new field of technologies because applications on this fields have started before a short time ( around 60 years ) from now . Artificial intelligence is not a human intelligence, and no more than human intelligen ce . The paper displays a brief history of (AI) in section 2 , and sums up the history and present situation of artificial intelligence . The first time AI concept was mentioned and the first time it became a reality . The paper divides the intelligent agent in to its Two main categories in section 3 , A machine who acts and behaves in a smart way needs to have a system that provides this to them . Software agent is the system if it was applied to a machine or device that moves and acts a Physical agent will be produced . The paper shows the aim and the goal of AI in section 4, and how it can make a huge difference in life . The ability of machines to perform difficult tasks instead of humans . Also ,The paper defines some of the Methods used in AI in section 5 . Semantic networks , Frames ,decision trees , Predicate Logic , neural networks are some of the methods that the paper will have . Furthermore , The paper also analyzes its development direction ,mainly discusses the development trends in two fields of artificial intelligence, such as, expert systems and Visual and audio recognition and understanding in section 6 .
3
Finally it will conclude with AI applications and its future studies in section 7 . Artificial intelligence has been deep into the social life in all fields; it has been and will continue to be inevitably changing our lives .
Artificial intelligence (AI) : 1.
Artificial Intelligence , the English abbreviation is AI . It is a new technological science . it attempts to understand the substance of intelligence, and produce a new intelligent machine could make reactions similar to the human intelligence, the research on the field of artificial intelligence include robot ,speec h recognition, image recognition , natural language processing and expert system . AL 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 . Artificial intelligence, by its essence, is the simulation of the information process of human thinking. There is two roads in stimulation th e first is structure simulation and the second is functional simulation . but still Artificial intelligence is not a human intelligence, and no more than human intelligence. Research scientists in Artificial Intelligence try to get machines to exhibit behavior that is called intelligent behavior that is observed in human beings .Some of behaviors are obstructive which scientists do not yet know how to solve them properly by computers .Machines require a certain system that is able to make them behave smartly which is called Intelligent agent.
A brief History of ( AI): 2.
Although AI is a new field of study it has roots in the past . The field of AI is generally held to have started at a conference in July 1956 at Dartmouth College when the phrase ´Artificial Intelligenceµ was first used. It was attended by many of those who became leaders in the field including John McCarthy, Marvin Minsky, Oliver Selfridge, Ray Solomonoff, Trenchard More, Claude Shannon, Nathan Rochester, Arthur Samuel, Allen Newell, and Herbert Simon . The roots of AI, may be found in Greek mythology .The concept of logical reasoning was i nvented by a Greek philosopher. Intelligent artifacts appear in literature since then, with real (and fraudulent) mechanical devic es actually made to behave with some degree of intelligence . An examples of a real mechanical device that behaves smartly printers , and modern clocks .In the 15th century printing was invented by a moving type . With the passage of days between the 15 th and the 16 th century clocks ,the first modern measuring machines were produced using lathes . After modern computers became available, following World War II ,the concept of thinking machines were firstly thought by Alan Turing , who proposed the Turing test which provides a definition of intelligence in a machine by comparing the intelligent behavior of a machine with that of the human . it has become possible to create programs that
4
perform difficult intellectual tasks. From these programs, general tools a re constructed which have applications in a wide variety of everyday problems , An example for this a robot was made in the late of 1990`s with auditory , visual and expressive system in human social interaction and to demonstrate simulated human emotion and appearance .The name Kismet comes from the Arabic, Turkish, Urdu, Hindi and Punjabi word meaning "fate" or sometimes "luck".
3. Two main categories for Intelligent agent :
Its divided into two broad categories : Software agent such as search engine used to search world wide web and find sites can provide information about requested subject , and the Physical agent (Robot) that can do tasks instead of human such as : painting . collecting , etc . Mobile robots are robots used in organizations to perform delivery tasks or prospect oil underwater .They have the capability to move around in their environment and are not fixed to one physical location. In contrast, industrial robots can't work as efficient as mobile robots . Mobile robots are the focus of a great deal of current research and almost every major university has one or more labs that focus on mobile robot research . Mobile robots are also found in industry, military and security environments. They also appear as consumer products, for entertainment or to perform certain tasks like vacuum. Furthermore , there is A humanoid robots which is an autonomous Mobile robots . There is still a lot of work before such robots can learn interact properly with the surroundings . intelligent software has a wide range of programmable languages that creates it but Two languages are specifically d esigned for AI : LISP and PROLOG.
4 .The aim of artificial intelligence :
The goal of work in artificial intelligence is to build machines that perform tasks normally are done by human intelligence like: to make systems that can work as experts . Also, to create a machine that behaves like human -To understand their surroundings through senses : sight , hearing , smell , taste. Scientists discovered how to make machines have the sight and hearing ability . They may discover in the future a robots that have all senses . Provide machines that can work instead of humans in Cumbersome tasks such as : welding , assembling , vacuuming « etc.
5. Methods used in (AI)-software agent- :
Artificial agent needs to be able to represent k nowledge so it can solve some problems related to the real world .Facts are represented in the computer or the smart machine as a data structure and its being manipulated by programs inside the computer .There is a lot of methods for representing facts . 1-A semantic network or net is one of the representation methods which is a graphic notation for representing knowledge in patterns of interconnected nodes and arrows (arcs) . Computer implementations of semantic networks were first
5
developed for artificial intelligence and machine translation . It uses Concepts (nodes)to represent the object and edges(arcs) to represent the relation between the two concepts .For example livings (super class ) a concept , we connect this concept to one of its( subclass es )humans by a relation ²an arrow- , which we can also connect it with one of the examples Peter ( Instance ) is Male . A Concept is divided to sets ²from the previous example : livings humans Peter .The relation could define an attribute of the concept such as : ( color , size , length « ). 2-Frame is other method which uses records to represent knowledge . The method uses a set of frames each frame has a concept and its definition either it was a super class or a sub class .Programs can handle frames more easily than semantic networks. It uses slots to represent the relation and objects . 3-Also , decision trees one of the methods used. It is a classifier in the form of a tree structure. It separates data into subsets and then analyses them into further subsets, and so on for few sublevels .The final subsets are precise. We Use a decision tree to predict categories for new events . Each decision node is labeled with an attribute. , each arc is labeled with a value for the nodes attribute, and each leaf node is labeled with a category .
Semantic nets are easily converted into decision trees, with the nodes representing goals and the links representing decisions that result from attaini ng one goal, and that lead to another goal
4-Furthermore , Predicate logic is other method to represent knowledge . Predicate logic, involves using standard forms of logical symbolism which have been familiar to philosophers and mathematicians for many decades . It can be represented in terms of logical formulae in which a predicate is applied to one or more arguments. Preposional logic is simpler language which uses five operators (NOT ),(OR),(AND),(IF« THEN ), and (IF AND ONLY IF ). Consider the following sentence: ``Every respectable villager worships God .'' A moment's reflection will reveal that this is ambiguous. Is it saying that there is one single God to which each respectable villager offers worship? Or does each worshipper have his or her own God, to which a fellow respectable villager may or may not be also praying? With predicate logic it is easy to reveal the nature of the ambiguity, by a device known as quantification . We can now use quantification to exhibit the ambiguity .Two quantifiers are common in predicate logic " For all " and " there exist ". 5-Neural networks : It is one of the methods used in machines in order to help it 'learn like humans . It is a parallel system, capable of resolving models that linear computing cannot. It is one of the newest signal-processing technologies. It`s system operates by simulating the operation of biological neural networks, in other words ,it`s system is based on the operation of biological neural system. Why would be necessary the imitation of artificial neural networks? Although computing these days is truly advanced, there are certain tasks that a program made for a common microprocessor is unable to perform; even so a software i mitation of a neural network can be made with their advantages and disadvantages .When creating a functional model of the biological neuron, there ar e three basic components of perceptrons . First, the synapses of the neuron are modeled as weights. The strength of the connection between an input and a neuron is noted by the value of
6
the weight. Negative weight values reflect inhibitory connections, whi le positive values designate excitatory .The next two components model the actual activity within the neuron cell. An adder sums up all the inputs modified by their respective weights. This activity is referred to as linear combination. Finally, an activat ion function controls the amplitude of the output of the neuron. The Computation in An Artificial Neural Network was designed to be adaptive, most often nonlinear (parallel) system that learns to perform a function from data. Adaptive means that the system can change itself in response to changes in its environment in such a way (21), normally called the training phase . After the training phase the Artificial Neural Network parameters are fixed and the system is deployed to solve the problem at hand (the testing phase ). The Artificial Neural Network is built with a systematic step-by-step procedure to optimize a performance criterion or to follow some implicit learning rules . The input/output training data are fundamental in neural network technology, because they convey the necessary information to "discover" the optimal operating point. The nonlinear nature of the neural network processing elements provides the system with lots of flexibility to achieve practical ly any desired input/output map. An input is presented to the neural network and a corresponding desired or target response set at the output (when this is the case the training is called supervised ). An error is composed from the difference between the desired response and the system output. This error information is fed back to the system and adjusts the system parameters in a systematic fashion (the learning rule). The process is repeated until the performance is acceptable. .They can be used in (OCR) optical character recognition , which intell igent agent is supposed to read any handwritings.
6. The development trends in AI : Expert systems :
Is an example of software programs that is based on software intelligent agents . They work instead of expert people . A wide variety of methods can be used to simulate the performance of the expert; however, common to most or all are : 1) the creation of a knowledge base which uses some knowledge representation structure to capture the knowledge of the Subject Matter Expert 2) a process of gathering that knowledge from the SME and codifying it according to the structure, which is called knowledge engineering and 3) once the system is developed, it is placed in the same real world problem solving situation as the human SME, typically as an aid to human workers or as a supplement to some information system. An example is medical expert system it is used to diagnose illnesses , to give the right treatments to illness , and tasks are normally made by a doctor .It is build on predefined knowedge about a certain field of expertise .A knowledge engineer build the expert system , who may not be an expert in the field , because he has expertise to know how to do the interview and how to interpret the answers so that can be used in building the knowledge . Some problems of uncertainty may occur due the following : a human, when reasoning, does not always make statements with 100% confidence for example "If reptile is green, then he is probably a frog" (after all, he might be a chameleon). so The MYCIN rule based expert system introduced a quasi-probabilistic approach called certainty factors . This type of reasoning can be imitated using numeric values called
7
confidences . For the previous example it is known that reptile is green, it might be concluded with 0.85 confidence that he is a frog; or, if it is known that he is a frog, it might be concluded with 0.95 confidence that he hops. These certainty factor (CF) numbers quantify uncertainty in the degree to which the available evidence supports a hypothesis. As each new piece of evidence becomes available an increases and decreases of CF is associated with a hypothesis . but builders must ensure that the system will give its users accurate advice or correct solutions to their problems .It can include seven components : User , User interface , Inference engine , knowledge base , fact database , explanation system , and knowledge base editor .Inference engine is the heart of an expert system : it communicates with the knowledge base , fact base , and the user interface . Explanation system, and knowledge base editor may not be included in some expert systems .
Perception ( image and language recognition and understanding ): Visual Recognition :
computer vision the science and technology of machines that see, where see in this case means that the machine is able to extract information from an image that is necessary to solve some tasks . Computer vision is concerned with the theory behind artificial systems that extract information from images. The image data can take many forms .It is used in many applications such as : interacting with humans . Computer vision is closely related to the study of biological vision. The field of biological vision studies and models the physiological processes behind visual perception in humans and other animals. Computer vision, on the other hand, studies and describes the processes implemented in software and hardware behind artificial vision systems. Interdisciplinary exchange between biological and computer vision has proven fruitfu l for both fields. Its relatively new field of study. In the early days of computing, it was difficult to process even moderately large sets of image data. It was not until the late 1970s that a more focused study of the field emerged. Computer vision covers a wide range of topics which are often related to other disciplines, and consequently there is no standard formulation of "the computer vision problem". Moreover, there is no standard formulation of how computer vision problems should be solved. Instead , there exists an abundance of methods for solving various well -defined computer vision tasks, where the methods often are very task specific and seldom can be generalized over a wide range of applications. Many of the methods and applications are still in the state of basic research , but more and more methods have found their way into commercial products, where they often constitute a part of a larger system which can solve complex tasks (e.g., in the area of medical images, or quality control and measure ments in industrial processes). In most practical computer vision applications, the computers are pre programmed to solve a particular task, but methods based on learning are now becoming increasingly common . Although it is an easy job for human to use their eyes , it turns out to be a hard task for an Artificial agent . How image is being processed ? It goes
8
through different steps . Edge detection is the first step in processing images .Edges can define boundaries between the object and its background .It indicates the contrast between the surfaces of the object and its background .It can find the boundaries between the object and its environment by using the intensity of the pixels . When a great deference of the pixels intensities is found ,there it will detect the edge . Segmentation is the second step is of image analysis .It divides the image into homogenous segments or areas .This step is similar to edge detection but the differences is that the edge detection finds the boundaries between the object and its background ,in segmentation boundaries between different areas inside the object are found . After this step is finished the object is divided into different areas .After that , the third step finding the depth of the object or objects in the image . Depth finding can help intelligent agent to gauge how far the object is from it .Two general methods are used for this purpose stereo vision and motion . a. Stereo vision uses one of the technique developed by human eyes to find the depth of the object . To have good distance recognition a hum needs two eyes . If the object is very close , two images created in your eyes are different , but if the object is far away the images are almost the same . So one of the tools use d in this method is to use to eyes or two cameras .The other method is called b .Motion it is based on taking several images to tell give clue to the distance of objects . For example , assume that the video shows a person moving towards a house . the distance between the person and the house ( close object ) will change but the distance between the person and a mountain will remain the same . Finding orientation is the forth step in analyzing images . One of techniques used is shading . Shading is based on the amount of light reflected from a surface that depends on the orientation of the su rface ( its position ) . Finally object recognition but to recognize an object it needs to have a model of the object in the memory . So it assume that the object is a compound of objects made of simple geometric shapes . Those shapes are stored in the memory .
Audio understanding :
A machine that can understand natural language can be really useful in our daily life . For example , it can replace a telephone operator . We can dived the task of machine that understands natural language into four consecutive steps : The first step is speech recognition .After the speech has been recognized the next step is syntactic analysis where the system defines where the word are to be grouped in the sentence . Why It·s a complex task ? For example John gave Sara the book = Sara was given the book by john . The system needs to interpret both sentences correctly and come with same conclusion . The third step is semantic analysis where it extracts the meaning of the sentence . In this step analysis cr eates a representation of the objects involved in the sentence , their relation , and their attributes . The last step is pragmatic analysis .This last step is needed to further clarify and to remove ambiguities .The machine has to understand the purpose of the sentence in order to act among understanding it .It has to make difference between requesting , promising , inquiring , and so on . Pragmatic analysis is required to find the purpose of the sentence . Sometimes a sentence is ambiguous after semantic analysis .Ambiguity can manifest itself in different ways . A word can have more than one function for example , the word hard can be both adjective or
9
a adverb . A word can have more than one meaning For example the word " ball " can have different meanings " football " or " ball room " .Also words with the same pronunciation can have different spelling and meaning .
Applications on AI :
Artificial intelligence has been used in a wide range of fields including medical diagnosis , stock trading , robot control , law, scientific discovery and toys . However, many AI applications are not perceived as AI : " A lot of cutting edge AI has filtered into general applications, often without being called AI because once something becomes useful enough and common enough it's not labeled AI anymore." . " Many thousands of AI applications are deeply embedded in the infrastructure of every industry ." In the late 90s and early 21st century, AI technology became widely used as elements of larger systems, but the field is rarely credited for these successes . Banks use artificial intelligence systems to organize operations , invest in stocks , and manage properties . In August 2001 , robots beat humans in a simulated financial trading competition . Financial institutions have long used artificial neural network systems to detect charges or claims outside of the norm , flagging these for human investigation . A medical clinic can use artificial intelligence systems to organize bed schedules , make a staff rotation , and provide medical information . Artificial neural networks are used for medical diagnosis. Robots have become common in many industries. They are often given jobs that are considered dangerous to humans. Robots have proven effective in jobs that are very repetitive which may lead to mistakes or accidents due to a lapse in concentration and other jobs which humans may find degrading. General Motors Corporation uses around 16,000 robots for tasks such as painting, welding, and assembly. Japan is the leader in using and producing robots in the world. In 1995, 700,000 robots were in use worldwide; over 500,000 of which were from Japan. AI has also been applied to video games . Various tools of artificial intelligence are also being widely deployed in homeland security, speech and text recognition, data mining, and e-mail spam filtering . Applications are also being developed for gesture recognition (understand ing of sign language by machines), individual voice recognition (, global voice recognition (from a variety of people in a noisy room), facial expression recognition. AL is used in medical computer vision or medical image processing. This area is characte rized by the extraction of information from image data for the purpose of making a medical diagnosis of a patient. This application area also supports medical research by providing new information, e.g., about the structure of the brain, or about the quali ty of medical treatments. Military applications are probably one of the largest areas for computer vision. The obvious examples are detection of enemy soldiers or vehicles and missile guidance . A second application area in computer vision is in industry, sometimes called machine vision, where information is extracted for the purpose of supporting a manufacturing process. One example is quality control where details or final products are being automatically inspected in order to find defects One of the newer application areas is autonomous vehicles, which include submersibles, landbased vehicles (small robots with wheels, cars or trucks), aerial vehicles, and unmanned aerial vehicles . The level of autonomy ranges from fully autonomous (unmanned) vehicles to vehicles where computer vision based systems support a driver or a pilot in various situations . Space exploration is already being made with
10
autonomous vehicles using computer vision, e. g., NASA's Mars Exploration Rover and ESA's Exo Mars Rover . Needless to say, the reality of today's AI technology is not even close to achieving the far-reaching visions of sci-fi. But could scientists one day - albeit at some distant far off point - create an artificial general intelligence (AGI), a machine that possesses human-level smarts? "Ultimately I think so," Daphne Koller, a professor in the Stanford AI Lab at the Computer Science Department of Stanford University in California, tells silicon.com. "Yes, I think ultimately it is possible. Ultimately, we will get machine learning technology to the point where the machine can adapt itself sufficiently that it's actually learning from lifelong experience, and in all realms, and I think that would eventually drive us towards that goal but it's going to take a very, very, very, very long time."
11
Terms used in the essay (AI) :
1-Ai (Artificial intelligence ) : is a study of programmed systems that can simulate , to some extent , human activities such as perceiving , thinking , learning , and acting . 2-Turing test :It¶s a test that compares the intelligent behavior of a human being with that of a computer by an interrogator . 3-Intelligent agent : A system that perceives its environment , learn from it , and interact with it intelligently . 4-Software agent : A set of programs that are designed to do particular tasks .such as classifying . 5-Physical agent (Robot ) : Is a programmable system that can be used to perform a variety of tasks .such as : painting , welding . 6- mobile robot : is an automatic machine that is capable of movement in a given environment . 7- humanoid robots : which is an autonomous Mobile robots . Robots that can behave like humans 8- industrial robots : usually consist of a jointed arm (multi-linked manipulator) and gripper assembly (or end effectors) that is attached to a fixed surface.
10 - Semantic networks :A directed graphs to represent knowledge . a-Concept = Vertices =Node( It can be thought of as a set or subset or a member ). b-Relations =Edges ( Arrows used to represent the relation between two concepts ).
12
11-Frames : A data structure ( records ) are used to represent knowledge . a-Object : ( It can be thought of as a set or subset or a member ). b-Slots : ( Fields in the data structure ).
NOTICE : We use the vocabulary Node in Semantic networks , and object in the Frames. AND Edges in Semantic networks , Slots in the Frames . 12- decision trees : It is a classifier in the form of a tree structure. It separates data into subsets and then analyses them into further subsets, and so on for few sublevels.
a- decision node: b- leaf node:
12- Predicate logic : A well-defined language developed via a long history of theoretical logic to represent complex facts . 13 - arguments is similar to, but not identical with
14- Propositional logic : A simpler language that is made up from a set of sentences that can be used to carry out reasoning about the world .
15- Quantification allows one to talk in a general way about all things of a certain class or about some particular but unspecified thing of a certain class
16- neural networks : It is one of the newest signal-processing technologies. It`s system operates by simulating the operation of biological neural networks.
17- perceptrons : is an artificial neuron to a single biological neuron . 16 -expert system : it performs tasks that normally needs a human expertise. 17- User interface : allows the user to interact with the system .The system accepts natural language. 18- inference engine : Is the heart of the system that uses the knowledge base and fact data base to infer the action to be taken . 19-Knowledge base : Is a collection of knowledge based on interview with experts in the relevant field of expertise .
13
20- fact database: :It is an case-based .For each case , the user inters the available or measured data into the fact database to be used by inference engine for that particular case 21- Explanation system : It is used to explain the rationale behind the decision made by the inference engine . 22-Knowledge editor : It is used to update the knowledge base if knew experiences has been obtained from experts in this filed . 23- perception : to understand receiving through sensing . 24-Edge detection : finding where the edges in the image are. 25- Segmentation : divides the image into homogenous areas . 26- homogenous segments : The intensity of pixals in these areas are almost the same . 27- Depth finding can help intelligent agent to gauge how far the object is from it. . a. Stereo vision uses one of the technique developed by human eyes to find the depth of the object
b-Motion it is based on taking several images to tell give clue to the distance of objects to determine how far are objects .
28- Finding orientation is the forth step in analyzing images . the aim of it to find the orentiation of an object . 28.1- . Shading is based on the amount of light reflected from a surface that shows the orientation of the surface ( its position ) . 29. speech recognition: The first stop in audio recognition process that divides the speech into words . 30. syntactic analysis : The second step in audio processing where the system defines where the word are to be grouped in the sentence 31. semantic analysis : The third step in audio recognition process where it extracts the meaning of the sentence. 32. pragmatic analysis .This last in audio recognition where is needed to further clarify and to remove ambiguities.
14
References :
In section 1 I used the following : y ^ Poole, Mackworth & Goebel 1998 , p. 1 (who use the term "computational intelligence" as a synony m for artificial intelligence). Other textbooks that define AI this way include Nilsson (1998), and Russell & Norvig (2003) (who prefer the term "rational agent") and write "The whole -agent view is now widely accepted in the field" ( Russell & Norvig 2003, p. 55) These textbooks are the most widely used in academic AI. See Textbooks at AI topics ^ This definition, in terms of goals, actions, perception and environment, is due to Russell & Norvig (2003). Other definitions also include knowledge and learning as additional criteria.
y
In section 2 : . Buchanan, Bruce G. A (Very) Brief History of Artificial Intelligence. AI mentioned reference .
. J. McCarthy, M. L. Minsky, N. Rochester, and C. E. Shannon, "A
Magazine 26(4):
Winter 2005, 53²60 * which I found in a website that used the
proposal for the Darthmouth summer research project on artificial intelligence", available at http://wwwformal.stanford.edu/jmc/history/dartmouth/dartmouth.html, August 31 1955.
15
. Bruce Buchanan and John McCarthy at the AI TOPICS booth at AAAI-02 in Edmonton, Canada (August 2002 available at http://www.aaai.org/AITopics/pmwiki/pm wiki.php/AITopics/BriefHistory
.
M. Turing, "Computing machinery and intelligence", Mind , vol. 59,
pp. 433-460,
http://www.ai.mit.edu/projects/sociable/baby -bits.html . . ^ a b c Peter Menzel and Faith D'Aluisio. Robosapiens. Cambridge: The MIT Press, 2000. Pg. 66 available in http://en.wikipedia.org/wiki/Kismet_(robot) In section 3 :. y y http://en.wikipedia.org/wiki/Mobile_robot foundation of computer science , behrouz forouzan and firouz mosharraf p.g.467 http://www.cengage.co.uk/forouzan/
IN section 5 : y y y y y )-foundation of computer science , behrouz forouzan and firouz mosharraf p.g.490 http://www.cengage.co.uk/forouzan/ oxford english for information technology ,Eric H. Glendinning , John McEwan p.g.22 http://www.cs.bham.ac.uk/research/projects/poplog/computers and thought/chap3/node6.html http://www.learnartificialneuralnetworks.com/ http://www.answers.com/topic/adaptive -system
In section 6: y http://en.wikipedia.org/wiki/Expert_system
In section 7: y y Computer Vision Online A good source for source codes, software packages, datasets, etc. related to computer vision foundation of computer science page 480 .second edition .
In section 8 :
16
y
y
Russell, Stuart J.; Norvig, Peter (2003), Artificial Intelligence: A Modern Approach (2nd ed.), Upper Saddle River, New Jersey: Prentice Hall, ISBN 0-13-790395-2, http://aima.cs.berkeley.edu/ Kurtzweil, Ray (2005), The singularity is near : when humans transcend biology, New York: Viking, ISBN 9780670033843
17
