CSCI 4410Introduction to Artificial Intelligence

What is AI?

Difficult to define “The Intelligence of a System is

inversely proportional to our understanding of it”

What is AI? making computer programs that appear to think?

the automation of activities we associate with human thinking, like decision making, learning ?

the art of creating machines that perform functions that require intelligence when performed by people ?

the study of mental faculties through the use of computational models ?

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

a branch of computer science that is concerned with the automation of intelligent behavior ?

anything in Computing Science that we don't yet know how to do properly ?

AI

“The art of creating machines that perform functions that require intelligence when performed by people.” (Kurzweil)

“The study of how to make computers do things at which, at the moment, people are better.” (Rich and Knight)

But what about creativity? Many would argue

machines are already writing rap music and reality shows

Rational Systems

How do we know how humans think? Introspection vs. psychological

experiments Brain research (scanning,

experiments, testing) Cognitive Science

Rational Systems

Humans are not always ‘rational’ Rational - defined in terms of

logic? Logic can’t express everything

(e.g. uncertainty) Logical approach is often not

feasible in terms of computation time - needs ‘guidance’

We will never get to intelligence with rules

Satisfiability

Rule systems must be checked This is the Satisfiability Problem NP-complete Checking all the states of a large

rule system is computationally expensive

Turing Test

Described by Alan Turing in 1950 A human judge engages in a

natural language conversation with a human and a machine

If the judge cannot reliably tell which is which, then the machine passes the Turing test.

The conversation is usually limited to text.

Turing Test

However…

Turing Test

A machine passing the Turing test may be able to simulate human conversation

Is this intelligence? how do we know humans don't

just follow rules? Blockhead – all paths Chinese room - rules

Can young children pass the test?

Turing Test

Turing test measures human-like behavior

Even if the Turing test is a good definition of intelligence, it may not indicate consciousness.

Does intelligence imply consciousness?

Practical AI

Do we care whether a system:Replicates human thought

processesMakes the same decisions as

humansUses purely logical reasoning

AI in Practice Medical advice system

Part-picking robots

Credit card fraud detection

Spam filters

Medical diagnosis, teleoperated/micro surgery

AI in Practice

Information retrieval, Google

Scheduling, logistics, supply chain management

Aircraft and pipeline inspection

Speech recognition, generation, translation

AI in Practice

And robots and chatbots

Heuristics

Two fundamental goals: finding algorithms with good run

times and optimal solutions.

But… these goals are often mutually exclusive

A heuristic is an algorithm that relaxes one or both of these goals

Heuristics

Special instances of the problem may cause the heuristic to produce poor results or run slowly

These instances may be rare Ex: sorting algorithms where the list

is already sorted Matching the heuristic to the

domain is important Heuristics are very common in

real world implementations.

Example – Spam Assassin Spam Assassin uses a wide variety of heuristic

rules to determine whether an email is a spam or ham Bayesian filter Blacklisting Regular expression matching

Modern Focus

Artificial intelligence can be considered under a number of headings: Search Representing Knowledge and

Reasoning Planning Uncertainty Learning Interacting with the Environment

(e.g. Vision, Speech, Robotics)

Search Search is the fundamental technique of AI.

Possible answers, decisions or courses of action are structured into an abstract space, which we then search.

Search is either "blind" or "informed": blind

we move through the space without worrying about what is coming next, but recognising the answer if we see it

informed we guess what is ahead, and use that

information to decide where to look next.

Desire for optimal solutions leads to heuristics

Knowledge Representation and Reasoning If we are going to act rationally in our environment,

then we must have some way of describing that environment. how do we represent what we know about the

world ?

how do we represent it concisely ?

how do we represent it so that we can get hold of the right piece of knowledge when we need it ?

how do we generate new pieces of knowledge ?

how do we deal with uncertain knowledge ?

Planning

Given a set of goals, construct a sequence of actions that achieves those goals:

often very large search space but most parts of the world are

independent of most other parts often start with goals and connect them

to actions no necessary connection between order

of planning and order of execution what happens if the world changes as we

execute the plan and/or our actions don’t produce the expected results?

Uncertainty

Given the set of “uncertain” information, how can we achieve the goals (and how certain are we of that answer).

How do we deal with uncertainty in our daily lives?

How can we make this more systematic How can we build systems that deal with

uncertainty How can we insure that the systems are

reasonable and correct

Learning If a system is going to act truly

appropriately, then it must be able to change its actions in the light of experience:

Generating new facts from old

How do we generate new concepts ?

How do we learn to distinguish different situations in new environments ?

Knowledge

Virtually all techniques benefit from ‘common sense’

CYC – a very large database of general purpose knowledge

Resolving Ambiguity – Ex. Consider the following pair of sentences:

Fred saw the plane flying over Zurich. Fred saw the mountains flying over Zurich.

Humans recognize that in the first sentence, "flying" refers to the plane

In the second sentence, "flying" almost certainly refers to Fred.

Traditional Natural Language systems will have difficulty resolving this syntactic ambiguity

Cyc knows that planes fly and mountains do not, and can reject nonsensical interpretations.