Artificial Intelligence 10-1-11. Where is the dog in this Image?

Artificial Intelligence

10-1-11

Where is the dog in this Image?

Artificial Intelligence• Artificial Intelligence (Book Def.) – The study of computer systems that

model and apply the intelligence of the human mind– Used to develop software and machines that emulate human qualities such as learning,

reasoning, communicating, seeing, and hearing

• Areas include– Expert systems– Natural language processing– Neural networks– Intelligent agents– Virtual reality and simulation devices– Pattern recognition– Fuzzy logic– Robotics

Knowledge Representation• Semantic network: A knowledge representation technique that represents the relations between

objects. It is a directed or undirected graph consisting of vertices, which represent concepts, and edges.

Gender

Person

Student

John

Male

234-576

ID

Sims

Dorm

Brown

Eye Color

Gender

Eye colorInstanceof

Instanceof

Instanceof

Instanceof

Instanceof

Lives in

Has aHas a

Has a

Instanceof

Is a

Search Trees• Search tree: A structure that represent alternatives in various situations

such as game playing

Breadth-First SearchDepth-First Search

Breadth First vs. Depth First Search

Depth First Breadth First

Breadth First vs. Depth First Search

Which type of search would return the result the fastest for:

M?K?D?G?

Expert Systems• Three components of an expert system

– Knowledge base• An expert system’s database of knowledge about a particular

subject

– Inference engine• The software that controls the search of the expert system’s

knowledge base and produces conclusions

– User interface• The display screen the user used to interact with the expert

system

Artificial Intelligence• Natural language processing

– Allows users to interact with a system using normal language.– Voice recognition – recognizing human words– Language comprehension – interpreting human communication– Voice synthesis – recreating human speech– Challenges of natural language processing?

• Intelligent agents– A form of software with built-in intelligence that monitors work

patterns, asks questions, and performs work tasks on your behalf

• Pattern recognition– Involves software that identify recurring patterns and maps the

pattern against patterns stored in a database

Artificial Intelligence• Fuzzy logic

– A method of dealing with imprecise data and uncertainty, with problems that have many answers rather than one

• Virtual reality– A computer-generated artificial reality that projects a person into a

sensation of 3-D space– Often used with simulators to represent the behavior of physical or

abstract systems

Background of Robotics

Idea of artificial people dates all the way back to Greek Mythology

One of the first recorded designs was by Da Vinci

What Classifies a Robot? Experts Say:1. Artificially created 2. Reacting to external environment3. Can manipulate environment4. Is programmable5. Can Move

What Are Robots Used For?

Right now Robots are used for

Entertainment

Car Production

Jobs Too Dangerous for Humans

Vacuum Cleaner (Like from the commercial)

Companionship to Humans (Aibo)

Many other things

What Could Robots Be Used For?

Future Plans for Robotics include:

Assistance to the Elderly or Disabled

Medical Field

Space

Personal Service Robots

Science Fiction and Robotics

Isaac Asimov

Three Laws of Robotics:

1. A robot may not injure a human being, or, through inaction, allow a human being to come to harm

2. A robot must obey the orders given it by human beings except where such orders would conflict with the First Law

3. A robot must protect its own existence as long as such protection does not conflict with the First or Second Law.

Can Robots act Ethically?

• Serious Questions Must be Raised

Decisions, Decisions

Computers have algorithms and strict rules to guide action

Human DecisionsNot based on rules aloneAlso judgment and conscience

If a robot could think ethically, whose ethics would it follow?

Robotics• The development and study of machines that can perform work that is

normally done by people• Subsumption architecture

• Commonly found in manufacturing plants and also in situations where people would be in danger– Nuclear plants– Assembly lines, especially paint lines– Checking for land mines– Fighting oil-well fires

Robotics• Two main Categories of Robots

– Fixed – stay put, generally have one specific task things around it move (assembly line)– Mobile – move about and interact with the environment around it.

• Mobile Robotics - the study of robots that move relative to their environment– Sense-Plan-Act (SPA) paradigm – steps of a mobile robot completing some action.

• (SENSING -> WORLD MODELING -> PLANNING -> CONTROL -> EXECUTION)• Sensing – sensor data input some knowledge from the outside world • World Modeling – interprets and models the input from sensing• Planning - Interpreted model is used generate a plan of action• Control – Robot’s control system (the hardware) is used to carry out the plan.• Execution – Plan carried out through execution

– Main challenge of SPA Paradigm – new sensory data comes in so fast and must be processed so fast that it is extremely difficult to use.

Weak & Strong AI• Weak vs. Strong A.I.

– Weak A.I. claims computers can be programmed to simulate human cognition

– Strong A.I. claims that computers can think on a level that is equal to or better than humans, and can also achieve consciousness• Cyc approach to strong A.I.

– A database in Austin, TX that holds 1.4 million basic truths– Plan is that Cyc will automatically make human-like

assumptions– Hope is that Cyc will learn on its own

• Cog approach to strong A.I.– MIT project that is a humanoid robot– Tries to identify and search for patterns instead of following

rules and facts

Testing Intelligence• Test for Human Intelligence

– In 1950, Allen Turing predicted computers would be able to mimic human thinking

– The Turing test determines whether the machine is human• Judge is in another location and doesn’t see the computer• If the computer can fool the judge, it is said to be intelligent

– Weak equivalence: The equality of two systems based on the results– Strong equivalence: The equality of two systems based on their

results and the process by which the results were reached

Turing Test

• Interrogator (C) must determine which respondent is a computer and which is human.