Artifical Intelligence

Intelligence

• Intelligence has been defined in many different ways

including as one's capacity for
 Logic
 Understanding It can be more generally
 self-awareness described as the ability
 Learning to perceive information, and to
retain it as knowledge to be
 emotional knowledge,
applied towards adaptive
 planning, behaviors within an environment
 creativity and or context.
 problem solving.
 What is AI?
• Views of AI fall into four categories:
– Systems that act like humans
– Systems that think like humans
– Systems that act rationally
– Systems that think rationally

• In this course, we are going to focus on systems that

act rationally, i.e., the creation, design and
implementation of rational agents.
•
 What is AI?
• A rationalist approach involves a combination
of mathematics and engineering.

• By distinguishing between human and rational

behavior, we are not suggesting that humans
are necessarily “irrational” in the sense of
“emotionally unstable” or “insane.”
 What is AI?
Acting humanly: The Turing Test approach

The Computer would need to possess the following capabilities:

 Natural language processing to enable it to communicate
successfully in English (or some other human language)
 Knowledge representation to store information provided
before or during the interrogation;
 Automated reasoning to use the stored information to
answer questions and to draw new conclusions
 Machine learning to adapt to new circumstances and to
detect and extrapolate patterns.
 Thinking humanly
The cognitive modeling approach
• get inside the actual workings of human minds.
There are three ways to do this:
• through introspection—trying to catch our own
thoughts as they go by
• through psychological experiments—observing a
person in action
• through brain imaging—observing the brain in
action.
 Thinking humanly
Allen Newell and Herbert Simon, “General Problem
Solver”
Thinking rationally: The “laws of thought”
approach
• The Greek philosopher Aristotle was one of the first to
attempt to codify “right thinking”.

• SYLLOGISM
• has two premises and one conclusion
• for example, “Ali is a man; all men are mortal; therefore, Ali is
mortal.”
• Negative example: “all birds lay eggs, hen lay eggs so hen is a
bird.”
These laws of thought were LOGIC supposed to govern the
operation of the mind; their study initiated the field called logic.
• Just for understanding we will discuss
knowledge represntation in detail in coming
lectures.
Thinking rationally: The “laws of thought”
approach
Logicians in the 19th century developed a precise notation for
statements about all kinds of objects in the world and the
relations among them.

Drawbacks:
There are two main obstacles to this approach.

1. not easy to take informal knowledge and state it in the

formal terms required by logical notation
2. a big difference between solving a problem “in principle”
and solving it in practice.
 Acting rationally: The rational agent
approach
• Rational behavior: doing the right thing
• The right thing: the optimal (best) thing that is expected to
maximize the chances of achieving a set of goals, in a given
situation
• Making correct inferences is sometimes part of being a
rational agent
Agents
 Agents
• An agent is anything that can be viewed as perceiving
its environment through sensors and acting upon that
environment through actuators.

• Human agent: eyes, ears, and other organs for sensors;

hands,legs, mouth, and other body parts for actuators

• Robotic agent: cameras and infrared range finders for

sensors; various motors for actuators
Next lectures will discuss agents their types and working
in detail
 Rational Agents
• A rational agent is one that acts so as to achieve the
best outcome or, when there is uncertainty, the best
expected outcome.
 Real AI
• A serious science.
• General-purpose AI like the robots of science
fiction is incredibly hard
– Human brain appears to have lots of special and
general functions, integrated in some amazing way
that we really do not understand at all (yet)
• Special-purpose AI is more doable
E.g., chess/poker playing programs, logistics planning,
automated translation, voice recognition, web search,
data mining, medical diagnosis, keeping a car on the
road, … … … … 16
 Artificial Intelligence
 Artificial intelligence (AI) is intelligence exhibited by machines.

 In computer science, an ideal "intelligent" machine is a

flexible rational agent that perceives its environment and takes
actions that maximize its chance of success at some goal.

 The term "artificial intelligence" is applied when a machine mimics

"cognitive" functions that humans associate with other human
minds, such as "learning" and "problem solving".
 Artificial Intelligence
 Capabilities currently classified as AI include successfully
understanding human speech, competing at a high level in strategic
game systems (such as Chess and Go), self-driving cars, and
interpreting complex data.

 AI research is divided into subfields that focus on specific problems

or on specific approaches or on the use of a particular tool or
towards satisfying particular applications.
 Weak AI
 Weak AI (also known as narrow AI) is non-sentient
artificial intelligence that is focused on one narrow
task.
 Weak AI is defined in contrast to either strong AI (a
machine with consciousness, sentience and mind) or
artificial general intelligence (a machine with the
ability to apply intelligence to any problem, rather
than just one specific problem).
 All currently existing systems considered artificial
intelligence of any sort are weak AI at most.
Example : SIRI
 Strong AI
 Strong AI is a term used to describe a certain
mindset of artificial intelligence development.
 Strong AI's goal is to develop artificial intelligence
to the point where the machine's intellectual
capability is functionally equal to a human's.
 This approach presents a solution to the problems
of symbolic attempts to create human intelligence
in computers.
 Strong AI
 Instead of trying to give the computer adult-like
knowledge from the outset, the computer would
only have to be given the ability to interact with the
environment and the ability to learn from those
interactions.
 As time passed it would gain common sense and
language on its own.
 This paradigm seeks to combine the mind and the
body, whereas the common trend in symbolic
programming (i.e. CYC) has been to disregard the
body to the detriment of the computer's intellect.
 Neat AI and Scruffy AI
 Neat and scruffy are labels for two different types
of artificial intelligence (AI) research.
 Neats consider that solutions should be elegant,
clear and provably correct and documentable.
 Scruffies believe that intelligence is too
complicated (or computationally intractable) to be
solved with the sorts of homogeneous system such
neat requirements usually mandate.
 Neat AI and Scruffy AI
 Much success in AI came from combining neat and
scruffy approaches.
 For example, there are many cognitive
models matching human psychological data built
in Soar and ACT-R.
 Both of these systems have formal representations
and execution systems, but the rules put into the
systems to create the models are generated ad hoc.