Analysis of Algorithm

Project Title: ARTIFICIAL INTELLIGENCE

Term Paper

Artificial Intelligence

Intelligence:

Intelligence is the computational part of the ability to achieve goals in the world. Varying kinds

and degrees of intelligence occur in people, many animals and some machines. It is the ability to

think and understand instead of doing things by instinct or automatically. It is the ability to learn

and understand, to solve problems and to make decisions.

Now thinking according to dictionary is

“Thinking is an activity of using your brain to consider a problem or to create an idea.”

Can computers can be intelligent? OR Can machines think?

“Artificial intelligence (AI) as a science makes machines do things that would require

intelligence if done by humans.”

However, the answer is not a simple Yes or No but rather a vague or fuzzy one.

What is Artificial Intelligence?

There is a huge amount of published research and popular literature in the field of AI (Artificial

Intelligence-a & b, n.d.; Minsky 1960; AI Journals & Associations, n.d.). John McCarthy coined

the phrase Artificial Intelligence as the topic of a 1956 conference held at Dartmouth (Buchanan,

n.d.)

Here are three definitions of AI. The first is from Marvin Minsky, a pioneer in the field. The

second is from Allen Newell, a contemporary of Marvin Minsky. The third is a more modern,

1990 definition, and it is quite similar to the earlier definitions.

In the early 1960s Marvin Minsky indicated that “artificial intelligence is the

science of making machines do things that would require intelligence if done by

men.” Feigenbaum and Feldman (1963) contains substantial material written by

Minsky, including “Steps Toward Artificial Intelligence” (pp 406-450) and “A

Selected Descriptor: Indexed Bibliography to the Literature on Artificial

Intelligence” (pp 453-475)

In Unified Theories of Cognition, Allen Newell defines intelligence as: the degree

to which a system approximates a knowledge-level system. Perfect intelligence is

defined as the ability to bring all the knowledge a system has at its disposal to

bear in the solution of a problem (which is synonymous with goal achievement).

This may be distinguished from ignorance, a lack of knowledge about a given

problem space.

Artificial Intelligence, in light of this definition of intelligence, is simply the

application of artificial or non-naturally occurring systems that use the

knowledge-level to achieve goals. (Theories and Hypotheses)

What is artificial intelligence? It is often difficult to construct a definition of a

discipline that is satisfying to all of its practitioners. AI research encompasses a

spectrum of related topics. Broadly, AI is the computer-based exploration of

methods for solving challenging tasks that have traditionally depended on people

for solution. Such tasks include complex logical inference, diagnosis, visual

recognition, comprehension of natural language, game playing, explanation, and

planning (Horvitz, 1990).

Artificial intelligence (AI) is a of the field of computer and information science. It focuses on

developing hardware and software systems that solve problems and accomplish tasks, such as

perception, reasoning and learning and develop systems to perform those tasks. The field of AI

includes studying and developing machines such as robots, automatic pilots for airplanes and

space ships, and “smart” military weapons.

Artificial Intelligence is the study of computer systems that attempt to model and apply the

intelligence of the human mind. It is the science and engineering of making intelligent machines,

especially intelligent computer programs. It is related to the similar task of using computers to

understand human intelligence.

Moreover it is:

1. Ability to interact with the real world, to perceive, understands, and act

E.g. speech recognition and understanding and synthesis

E.g. image understanding

E.g. ability to take actions, have an effect

2. Reasoning and Planning

Modeling the external world, given input

Solving new problems, planning, and making decisions

Ability to deal with unexpected problems, uncertainties

3. Learning and Adaptation

We are continuously learning and adapting

Our internal models are always being “updated”

E.g. learning to categorize.

AI involves Perceiving, recognizing, understanding the real world, Reasoning and planning

about the external world, Also Learning and adaptation. AI researchers responded by developing

new technologies, including streamlined methods for eliciting expert knowledge, automatic

methods for learning and refining knowledge, and common sense knowledge to cover the gaps in

expert information. These technologies have given rise to a new generation of expert systems

that are easier to develop, maintain, and adapt to changing needs.

Goals of AI:

The definition of AI gives four possible goals to pursue:

1. Systems that think like humans.

2. Systems that think rationally.

3. Systems that act like humans

4. Systems that act rationally

Traditionally, all four goals have been followed and the approaches were:

Most of AI work falls into category (2) and (4).

General AI Goal

Replicate human intelligence: still a distant goal.

Solve knowledge intensive tasks.

Make an intelligent connection between perception and action.

Enhance human-human, human-computer and computer to computer

Interaction / communication.

Engineering based AI Goal Develop concepts, theory and practice of building intelligent machines

Emphasis is on system building.

Science based AI Goal Develop concepts, mechanisms and vocabulary to understand biological

Intelligent behavior.

Emphasis is on understanding intelligent behavior.

AI Approaches:

The approaches followed are defined by choosing goals of the computational model, and basis

for evaluating performance of the system.

1. Cognitive science : Think human-like

• An exciting new effort to make computers think; that it is, the machines with

minds, in the full and literal sense.

• Focus is not just on behavior and I/O, but looks at reasoning process.

• Computational model as to how results were obtained.

• Goal is not just to produce human-like behavior but to produce a sequence of

steps of the reasoning process, similar to the steps followed by a human in

solving the same task.

2. Laws of Thought : Think Rationally

• The study of mental faculties through the use of computational models; that it

is, the study of the computations that make it possible to perceive, reason, and

act.

• Focus is on inference mechanisms that are probably correct and guarantee an

optimal solution.

• Develop systems of representation to allow inferences to be like “Socrates is a

man. All men are mortal. Therefore Socrates is mortal.”

• Goal is to formalize the reasoning process as a system of logical rules and

procedures for inference.

• The issue is, not all problems can be solved just by reasoning and inferences.

3. Turing Test : Act Human-like

• The art of creating machines that perform functions requiring intelligence when

performed by people; that it is the study of, how to make computers do things

which at the moment people do better.

• Focus is on action, and not intelligent behavior centered around representation

of the world.

• A Behaviorist approach is not concerned with how to get results but to the

similarity to what human results are.

• Goal is to develop systems that are human-like.

4. Rational Agent : Act Rationally

• Tries to explain and emulate intelligent behavior in terms of computational

processes; that it is concerned with the automation of intelligence.

• Focus is on systems that act sufficiently if not optimally in all situations.

• It is passable to have imperfect reasoning if the job gets done.

• Goal is to develop systems that are rational and sufficient.

Different Types of Artificial Intelligence

1. Knowledge representation and Commonsense knowledge

2. Automated planning and scheduling

3. Machine learning

4. Natural language processing

5. Machine perception, Computer vision and Speech recognition

6. Affective computing

7. Computational creativity

8. Artificial general intelligence and AI-complete

Machine learning

Machine:

A machine is a tool containing one or more parts that uses energy to perform an intended action.

Learning:

Learning is the act of acquiring new, or modifying and reinforcing, existing knowledge,

behaviors, skills, values, or preferences and may involve synthesizing different types of

information.

In 1959, Arthur Samuel defined machine learning as a "Field of study that gives computers the

ability to learn without being explicitly programmed".

What is machine learning?

Ability of a machine to improve its own performance through the use of software that employs

artificial intelligence techniques to mimic the ways by which humans seem to learn, such as

repetition and experience.

Machine learning can be considered a subfield of computer science and statistics. It has strong

ties to artificial intelligence and optimization, which deliver methods, theory and application

domains to the field.

Machine learning and statistics:

ML (Machine learning and Statistics) are closely interrelated. From methodological principles to

theoretical tools, ideas of ML have had a lengthy pre-history in Stat. Michael I. Jordan suggested

the Data science as a placeholder to call the overall field.

Learning from Data:

Data is recorded from some real-world phenomenon.

What might we want to do with that data?

Prediction:

- What can we predict about this phenomenon?

Description: - How can we describe/understand this phenomenon in a new way?

Types of problems:

1. Supervised learning

2. Unsupervised learning

3. Reinforcement learning

Reinforcement learning:

It is learning from interaction with an environment; from the consequences of action, rather than

from explicit teaching. RL is conducted within the mathematical framework of Markov decision

processes (MDPs).

Supervised learning:

Trainingdataincludesboththeinputandthe desiredresults.

Forsomeexamplesthecorrectare knownandaregivenininputtothemodelduring

thelearningprocess. The constructionofapropertraining, validationand testset is

crucial.Thesemethodsareusuallyfastandaccurate

Unsupervised learning: The data have no target attribute. We want to explore the data to find some intrinsic structures in

them. Themodelisnotprovidedwiththecorrectresultsduringthetraining. It canbe

used toclustertheinputdatainclassesonthebasisoftheirstatisticalpropertiesonly. It is further divided into:

1. Clustering

2. Hidden Markov models

3. Blind signal separation

Clustering:

Clustering of data is a method by which large sets of data are grouped into clusters of smaller

sets of similar data.

The example below demonstrates the clustering of balls of same colors. There are a total of 9

balls which are of three different colors. We are interested in clustering of balls of the three

different colors into three different groups.

The balls of same color are clustered into a group as shown below:

Thus, we see clustering means grouping of data or dividing a large data set into smaller data sets

of some similarity.

A clustering algorithm has following types:

1. Partitional clustering

• k-Means (and EM)

• k-Medoids

2. Hierarchical clustering

• Agglomerative

• Divisive

• BIRCH

Examples of Clustering Applications:

Marketing: Help marketers discover distinct groups in their customer bases, and then use

this knowledge to develop targeted marketing programs

Land use: Identification of areas of similar land use in an earth observation database.

Insurance: Identifying groups of motor insurance policy holders with a high average

claim cost.

Urban planning: Identifying groups of houses according to their house type, value, and

geographical location.

Seismology: Observed earth quake epicenters should be clustered along continent faults

K-means

K-means is a partitional clustering algorithm

Let the set of data points (or instances) D be

{x1, x2, …, xn},

where xi = (xi1, xi2, …, xir) is a vector in a real-valued space X Rr, and r is the number

of attributes (dimensions) in the data.

The k-means algorithm partitions the given data into k clusters.

Each cluster has a cluster center, called centroid.

k is specified by the user

Works when we know k, the number of clusters we want to find

Randomly pick k points as the “centroids” of the k clusters

Loop:

o For each point, put the point in the cluster to whose centroid it is closest

o Recomputed the cluster centroids

o Repeat loop (until there is no change in clusters between two consecutive

iterations.)

K-means Algorithm:

Algorithm k-mean (k,D)

1. Choose k data point as the initial centroids (cluster centers)

2. Repeat

3. For each data point x ∈ to D do

4. Compute the distance from x each centroid.

5. Assign x to the closest centroid //a centroid represent

a cluster

6. endfor

7. re-compute the centroid using the current cluster membership

8. Until the stopping criterion is met

Example with Explanation:

Random Selection of k and cluster assignment

Draw distance from two pints and draw perpendicular bisector

The clustered will be colored According to centroids base on perpendicular bisector;

left side of cluster line give the red colors and right side are colored yellow

Now will take the average of the each cluster, the average will be new position of the centroid.

And the centroid move to new position, this is first iterations

Now draw distance from two centroids and draw perpendicular bisector

Now the clustered will be colored according to centroids base on perpendicular bisector;

left side of cluster line give the red colors and right side are colored yellow

Now will take the average of the each cluster, the average will be new position of the centroid.

And the centroid move to new position, this is second iterations.

Now draw distance from two centroids and draw perpendicular bisector

Now the clustered will be colored according to centroids base on perpendicular bisector and will

take the average of the each cluster, the average will be new position of the centroid.

And the centroid move to new position, this is third iterations.

Again draw distance from two pints and draw perpendicular bisector

Again it will take the average of each cluster and at this time centroids average does not

change/move. So this it stop. And it is our fourth iterations

Time Complexity of K-Mean Algorithm:

Complexity is O (n * K * I)

• n = number of points,

• K = number of clusters,

• I = number of iterations,

Applications of AI:

1. Game playing

• Games are Interactive computer program, an emerging area in which the goals

of human-level AI are pursued.

• Games are made by creating human level artificially intelligent entities, e.g.

enemies, partners, and support characters that act just like humans.

2. Speech Recognition

• A process of converting a speech signal to a sequence of words;

• In 1990s, computer speech recognition reached a practical level for limited

purposes.

• Using computers recognizing speech is quite convenient, but most users find

the keyboard and the mouse still more convenient.

• The typical usages are :

◊ Voice dialing (Call home)

◊ Call routing (collect call)

◊ Data entry (credit card number)

◊ Speaker recognition

3. Understanding Natural Language: Natural language processing (NLP) does automated generation and understanding

of natural human languages.

• Natural language generation system:

Converts information from computer databases into normal-sounding

human language.

• Natural language understanding system:

Converts samples of human language into more formal representations

that are easier for computer programs to manipulate.

• Some major tasks in NLP:

◊ Text-to-Speech (TTS) system:

Converts normal language text into speech.

◊ Speech recognition (SR) system:

Process of converting a speech signal to a sequence of words.

◊ Machine translation (MT) system:

Translate text or speech from one natural language to another.

◊ Information retrieval (IR) system:

Search for information from databases such as Internet or World

Wide Web or Intranets.

4. Computer Vision

• It is a combination of concepts, techniques and ideas from: Digital Image

Processing, Pattern Recognition, Artificial Intelligence and Computer

Graphics.

• The world is composed of 3-D objects, but the inputs to the human eye and

computers' TV cameras are 2-D.

• Some useful programs can work solely in 2-D, but full computer vision

requires partial 3-D information that is not just a set of 2-D views.

• At present there are only limited ways of representing 3-D information

directly, and they are not as good as what humans evidently use.

• Examples

◊ Face recognition: the programs in use by banks

◊ Autonomous driving: The ALVINN system, autonomously drove a van

from Washington, D.C. to San Diego, averaging 63 mph day and night,

and in all weather conditions.

◊ Other usages: Handwriting recognition, Baggage inspection,

Manufacturing inspection, Photo interpretation, etc.

5. Expert Systems

Systems in which human expertise is held in the form of rules

• It enables the system to diagnose situations without the human expert being

present.

• A Man-machine system with specialized problem-solving expertise. The

"expertise" consists of knowledge about a particular domain, understanding of

problems within that domain, and "skill" at solving some of these problems.

• Knowledge base; A knowledge engineer interviews experts in a certain

domain and tries to embody their knowledge in a computer program for

carrying out some task.

• One of the first expert systems was MYCIN in 1974, which diagnosed

bacterial infections of the blood and suggested treatments.

• Expert systems rely on knowledge of human experts, e.g.

◊ Diagnosis and Troubleshooting: deduces faults and suggest corrective

actions for a malfunctioning device or process

◊ Planning and Scheduling: analyzing a set of goals to determine and

ordering a set of actions taking into account the constraints; e.g. airline

scheduling of flights.

◊ Financial Decision Making: an advisory program assists bankers to

make loans, Insurance companies to assess the risk presented by the

customer, etc.

◊ Process Monitoring and Control: analyzes real-time data, noticing

anomalies, predicting trends, and controlling optimality and do failure

correction.

6. Robotics

A Robot is an electro-mechanical device that can be programmed to perform manual

tasks or a reprogrammable multi-functional manipulator designed to move materials,

parts, tools, or specialized devices through variable programmed motions for

performance of variety of tasks. An „intelligent‟ robot includes some kind of sensory

apparatus that allows it to respond to change in its environment.

Daily Life Examples:

Post Office:

Automatic address recognition and sorting of mail

Banks:

Automatic check readers, signature verification systems

Automated loan application classification

Customer Service:

Automatic voice recognition

The Web:

Identifying your age, gender, location, from your Web surfing

Automated fraud detection

Digital Cameras:

Automated face detection and focusing

Computer Games:

Intelligent characters/agents

Speech synthesis, recognition and understanding:

Very useful for limited vocabulary applications

Robotics

Limitations of AI

It cannot understand natural language robustly (e.g., read and understand

articles in a newspaper)

Surf the web

Interpret an arbitrary visual scene

Learn a natural language

Construct plans in dynamic real-time domains

Exhibit true autonomy and intelligence

Still need greater software flexibility

To date, all the traits of human intelligence have not been captured and

applied together to spawn an intelligent artificial creature.

Currently, Artificial Intelligence rather seems to focus on lucrative domain

specific applications, which do not necessarily require the full extent of AI

capabilities.

There is little doubt among the community that artificial machines will be

capable of intelligent thought in the near future.

CONCLUSION

In its short existence, AI has increased understanding of the nature of intelligence and provided

an impressive array of application in a wide range of areas. It has sharpened understanding of

human reasoning and of the nature of intelligence in general. At the same time, it has revealed

the complexity of modeling human reasoning providing new areas and rich challenges for the

future.

We conclude that if the machine could successfully pretend to be human to a knowledgeable

observer then you certainly should consider it intelligent. AI systems are now in routine use in

various field such as economics, medicine, engineering and the military, as well as being built

into many common home computer software applications, traditional strategy games etc.

References:

1. "Artificial Intelligence", by Elaine Rich and Kevin Knight, (2006), McGraw Hill companies

Inc.

2. "Artificial Intelligence: A Modern Approach" by Stuart Russell and Peter Norvig, (2002),

Prentice Hall.3. "Computational Intelligence: A Logical Approach", by David Poole, Alan

Mackworth, and Randy Goebel, (1998), Oxford University Press

4. "Artificial Intelligence: Structures and Strategies for Complex Problem Solving", by George

F. Luger, (2002), Addison-Wesley.

5. "AI: A New Synthesis", by Nils J. Nilsson, (1998), Morgan Kaufmann Inc.

6. "Artificial Intelligence: Theory and Practice", by Thomas Dean, (1994).

7. Related documents from open source, mainly internet:

a. http://en.wikipedia.org/wiki/Artificial_intelligence

b. https://www.youtube.com/watch?v=4shfFAArxSc

c. https://www.youtube.com/watch?v=_aWzGGNrcic

d. https://www.youtube.com/watch?v=0MQEt10e4NM

e. https://www.youtube.com/watch?v=aiJ8II94qck

f. https://www.youtube.com/watch?v=l77Au76TOok

g. https://www.youtube.com/watch?v=-07-iszyjM0

h. https://www.youtube.com/results?search_query=unsupervised+learning+tutorial

i. http://www.cs.gsu.edu/~cscyqz/courses/ai/aiLectures.html

j. http://www.eecs.qmul.ac.uk/~mmh/AINotes/

k. http://bookboon.com/en/artificial-intelligence-ebooks

l. http://ubiquity.acm.org/article.cfm?id=1041064

m. http://allquestionanswers.blogspot.com/2012/04/disadvantages-of-artificial.html

n. http://papers.nips.cc/paper/2601-the-correlated-correspondence-algorithm-for-

unsupervised-registration-of-nonrigid-surfaces.pdf

o. http://www.heppenstall.ca/academics/doc/370/CIS370.doc

p. http://pages.uoregon.edu/moursund/Books/AIBook/AI.doc