Introduction to Computers/AI

Course Navigation

Theory
There is no single unifying theory of Artificial intelligence, however a number of approaches can be seen below.

Alan Turing
Alan Turing Video

Alan Turing is the father of computer science, including artificial intelligence. He was an English mathematician, logician, and cryptographer who used artificial intelligence to break Nazi codes during World War II. Alan_turing

On a side note, Alan died at the age of 41. On June 7th, 1954, he committed suicide by cyanide poisoning. 

Turing Test


"The phrase “The Turing Test” is most properly used to refer to a proposal made by Turing (1950) as a way of dealing with the question whether machines can think." A behavioral test is conducted for the presence of mind, thought, or intelligence in machines. The test takes place between a human judge, another human and a computer. The human has a natural conversation with both the computer and the other human. If the judge is unable to decide who is the computer and who is the human, the computer has passed the test.

Turing_test 

fuzzy logic (probabilities)
Fuzzy logic is a method of dealing with imprecise data with problems that may have one or more answers. It ranks potential answers by their probability. Many problems arise in the process of using probability to rank and solve problems, most of these problems arise from the fact that in many cases these rankings are subjective or relate to moral choices. 

A.L.I.C.E.


Artificial Linguistic Internet Computer Entity is a free, open source software program that is used for AI (Artificial Intelligence). That “chat robot software” gives you an illusion that you are chatting with a real person. A.L.I.C.E. contains AIML which is Artificial Intelligence Markup Language. A.L.I.C.E. is a program that uses heuristical patterns to match inputs from conversions to communicate with humans.Artificial_Linguistic_Internet_Computer_Entity

Weak AI
Weak AI (artificial intelligence) makes the claim that computers can be programmed to simulate human cognition. An important concept of "Weak AI" is brute force: a technique for solving a complex problem by using a computer's fast processing capability to repeat a simple procedure many times. For example, a chess playing program will calculate all the possible moves that can apply to a given situation and then choose the best one; it does not analyze and strategize the way a human player does.

cyc
Cyc uses facts and rules in a database. The goal is to have Cyc automatically make the same connection as humans do. Cyc has been fed database of 1.4 million facts and rules and knows as much as a 12 year old. One day, cyc will learn on its own.

Strong AI
Strong AI (artificial intelligence) claims that computers can be made to think on a level that is at least equal to humans and possibly even be conscious of themselves.

Requirements of Strong AI:

Intelligent machines should be able to integrate these skills towards a common goal:

1) Reason this means they must use strategies, solve puzzles and make judgments. 2) Must represent knowledge, this includes commonsense knowledge. 3) Plan. 4) Learn. 5) Communicate in a natural language. 6) Perceive. 7) Social intelligence. 8) Able to move and manipulate objects, also known as robotics.

Strong AI is a system that can perform all these tasks as humans do or better. Strong_AI

cog
Cog does not follow predetermined sets of rules but rather tries to identify and search for patterns.

Mimic Human processes
Artificial Intelligence is a branch of Science which deals with helping machines find solutions to complex problems in a more human-like fashion. This generally involves borrowing characteristics from human intelligence, and applying them as algorithms in a computer friendly way. A more or less flexible or efficient approach can be taken depending on the requirements established, which influences how artificial the intelligent behaviour appears. A branch of AI deals with how machince can stimulate human behaviour, its called the Automata Theory.

Automata Theory, concept that describes how machines mimic human behavior. The theory proposes that human physical functions and behavior can be simulated by a mechanical or computer-controlled device. Applications of automata theory have included imitating human comprehension and reasoning skills using computer programs, duplicating the function of muscles and tendons by hydraulic systems or electric motors, and reproducing sensory organs by electronic sensors such as smoke detectors.

Neural networks
Neural networks try and mimic a brain by having many microchips each representing a neuron, and connections between them representing synapses. They use fuzzy logic processor and AI software. This then takes inputs and converts them to outputs with something similar to human logic [page 447]. Processors that arrive at the correct answer as determined by the programmers are kept, and the processors that do not are removed from the system. This is also how a human brain develops.

Neural Networks are used to do tasks such as
 * Function approximation
 * regression analysis
 * time series prediction
 * modelling

Less common
Of the AI applications that we use, neural networks are comparatively rare, however, they are already being used in a variety of situations. Hospitals use neural networks to diagnose patients who complain of the same symptoms. Banks also use it to spot irregularities in purchasing patterns, to detect fraud or stolen credit cards.

searching
Involves taking something that is being input and trying to match it to an exhaustive list of possible matches. (Example: Writing an E with a stylus on my Palm and the Palm recognizes the drawing formating as an E by searching all the letters it could be)

heuristics
Heuristics are "rules of thumb" taught to the computer. It is a method for helping in the solving of a problem. Heuristic

(Example: Writing an E with a stylus on my Palm and the Palm recognizes the drawing formating as an E by knowing that an E is like a C but with a horizontal spike in the middle)

pattern recognition


Pattern recognition is taking raw data and recognizing the pattern to make letters and numbers. It is used when writing in a PDA.

Example: Writing an E with a stylus on my Palm and the Palm recognizes the drawing formating as an E by noticing the similarity - but not exactness - that the user draws an E

Pattern recognition is used in data mining to discover previously unnoticed patterns; in facial recognition to identify faces, and in hand-writing recognition, fingerprint identification, robot vision, and automatic voice recognition.

Pattern recognition is studied in many diverse fields including the following; computer science, psychology and ethology.Pattern_recognition

learning
Machine learning refers to a system capable of the autonomous acquisition and integration of knowledge. This capacity to learn from experience, analytical observation, and other means, results in a system that can continuously self-improve and thereby offer increased efficiency and effectiveness.

(Example: Writing an E with a stylus on my Palm and the Palm recognizes the drawing formating as an E by noticing how a specific users always writes an E and adding this extra information to the heuristics already provided)

LISP
LISP is a highly portable, industrial strength programming language used by serious application developers. It's an acronym which stands for "List Processing". It was designed for easy manipulation of data strings. (en.wikipedia.org/wiki/*Lisp)

- Is a 3rd generation language used to make AI Programs

This serves as a means to write natural and expert systems programs which use AI to rank possibilities of answers to users questions.

Prolog
Is a programming language with a strongly declarative style which is based on logic-rules paradigm. It's an example of a declarative language. Its a general purpose language which is especially associated with Artificial Intelligence and computational linguistics. http://en.wikipedia.org/wiki/Prolog

speech recognition
is the process of converting a speech signal to a sequence of words in the form of digital data, by means of an algorithm implemented as a computer program. Speech recognition applications that have emerged over the last few years include voice dialing (e.g., "Call home")etc. Speech_recognition

'Speaker Recognition' is a bit different then speech recognition in that it looks to decipher the voice, tone, pitch etc of a person rather then the actual words that the person is saying. (wikipedia, 2008)

Watch the video on youtube about speech recognition: http://www.youtube.com/watch?v=2Y_Jp6PxsSQ

parsing
Parsing takes parts of words (tokens) and pieces them together to get a proper grammatical word. (ex: cat i pil ar)

In computer science and linguistics, parsing (as it is formally called "syntactic analysis")is the process of analyzing a sequence of words (tokens) to determine its grammatical structure with respect to a given format. The parser often uses a separate analyser to creat tokens from the sequent of input characters. parsers may be programmed by hand or may be semi-automatically generated by a tool from a grammar written in form.

Parsin is also an earlier term for the diagramming of sentences of languages and is used in languages such as the Romance language.

lookup
Looking up all the possibilities and then rating them.

A systematic way of formulating the possibilities of the proper word being used.

speech production
Speech production is not artificial intelligence. Word pronunciation are preprogrammed to respond to written text.

The production of speech is widely described as a two-level process. In the first stage the sound is initiated and in the second stage it is filtered on the second level. The lungs and the associated muscles act as the source of air for exciting the vocal mechanism. The muscle force pushes air out of the lungs (shown schematically as a piston pushing up within a cylinder) and through the trachea. When the vocal cords are tensed, the air flow causes them to vibrate, producing so-called voiced speech sounds. When the vocal cords are relaxed, in order to produce a sound, the air flow either must pass through a constriction in the vocal tract and thereby become turbulent, producing so-called unvoiced sounds, or it can build up pressure behind a point of the total closure within the vocal tract, and when the closure is opened, the pressure is suddenly and abruptly release, causing a brief transient sound. 

OCR
OCR stands for Optical Character Recognition. It is the mechanical or electronic translation of images of handwritten or typewritten text into machine-editable text. E.G. scanner. link!!!

Is a field of research in pattern recognition. Optical_character_recognition

Special OCR characters appear on utility bills and price tag bills on department store merchandise. OCR software can deal with almost all printed characters, but script fonts and handwriting still present problems.

Optical Character Recognition is an ideal ability for many companies. This allows us to publish items and be able to search the text of a scanned document for keywords and other meta-data. Optical_character_recognition

hand writing recognition
The computer receives intelligence through a pen by written input commonly used for PDA's and video games. [Text, 262]

This technology is currently limited by the language of the operating system. If you are running an English recognition, your input of different languages will not be recognized.

Sometimes called ICR (Intelligent Character Recognition)

face recognition
This is a system on the computer that can identify someone from the metrics of their face commonly used in US Biometric photos.

Used in security systems and by the authorities to catch criminals Facial_recognition_system

agents
A software agent is a piece of software that acts on behalf of you or implies your authority to decide and activate themselves if an action is appropriate. They can collect information from the web according to topics you select for, or in the future it will even make dentist appointments for you according to openings in your calendar and the dentist's calendar. They act just like an Artificial Intelligence and use learning and reasoning to decide.(http://en.wikipedia.org/wiki/Software_agent)

expert system
interactive programs that assist users in finding solutions to problems, in place of a human expert's assistance. - 3 components are: knowledge base, inference engine and user interface.

An example is the help feature in MS Word.

knowledge base
Knowledge base is an expert system's database of knowledge on a particular subject.

A knowledge base is a database for knowledge management. It provides the means for the computerized collection, organization, and retrieval of knowledge. There are two types of major knowledge bases:

Machine-readable knowledge bases which store knowledge in a computer-readable form. Knowledge_base

inference engine
A system that allows the user to inquire about a topic and the system will produce results based on facts and rules It queries the relationships between knowledge items to find the users most likely to answer

user interface
This is the display screen; allows the user to communicate by asking questions and receive answers. The user interface interacts with a system or a particular device (computer program or orther complex tools).

ELIZA
Joseph Weizenbaum came up with the computer program ELIZA in 1966. It was named after a character in a play, and it copied a Rogerian therapist mostly by turning the patient's statements into questions for the patient. An example is the response to "My head hurts" might be "Why do you say your head hurts?"

(http://en.wikipedia.org/wiki/ELIZA)

AARON
Aaron is a type of artificial intelligence that was created by Harold Cohen. It is available as a screen saver that creates original fine art. link!!!

Robots
A robot performs functions that humans find difficult through automatic device. E.G. R2D2 or C3P0 And its more efficient in the tasks. Robots are used for various tasks such as assembly line production. A robot is an electro-mechanical device. link

Deep Blue (chess)
The second chess match between IBM's Deep Blue and Kasparov in the Spring of 1997 resulted in victory for Deep Blue. This in turn led to discussion and opinion in the press concerning the significance of this and the relation between Human and Machine or Computational Intelligence. 

Kasparov still claimed victory over machine with his earlier match with Deep Blue, which totals to a score of 6.5 over 5.5.

Driverless cars
The driverless car concept embraces an emerging family of highly automated cognitive and control technologies, ultimately aimed at a full "taxi-like" experience for car users, but without a human driver. Together with alternative propulsion, it is seen by some as the main technological advance in car technology by 2020.

It can achieved in various ways, either dedicated routes of travel that are pre-planned, or vehicles that are capable of precisely recognizing and executing drive commands. The self parking Lexus LS460L is one small step in this technology.

There are many problems associated with driverless cars. Technical problems include the design of sensors and control systems required to make the car work. Getting people to trust the car and getting permission for the cars to operate on public roads is the other half of the problem. There are four key areas to focus design on: sensors, navigation, motion planning and control of the vehicle itself.

Toshiba ApriPoko Robot

 * 11-inch-tall robot
 * Voice-activated remote control that uses AI.

A website describes ApriPoko: "If you pick up your TV's remote and start pressing buttons, ApriPoko will ask what you're doing and then memorize the IR codes associated with your actions. The next time around, you can just say "turn on the TV" and ApriPoko will take matters from there." 

Course Navigation