Download as pptx, pdf, or txt
Download as pptx, pdf, or txt
You are on page 1of 30

COMP6275 – Artificial Intelligence

Week 1
Overview
LEARNING OUTCOMES

At the end of this session, students will be able to:


o LO1 : Describe what is AI, identify concept of intelligent agent and various
intelligent
search algorithms to solve the problems
CONTENT OUTLINE

1. Artificial Intelligence (AI)


2. Foundations of AI
3. Intelligent Agent
4. Concept of Rationality
5. Properties of Environment
6. Structure of Intelligent Agents
7. Summary
Artificial Intelligence
Thinking Humanly Thinking Rationally
“The exciting new effort to “The study of mental faculties
make computers thinks … through the use of
machine with minds, in the computational models”
full and literal sense” (Charniak et al. 1985)
(Haugeland, 1985)
Acting Humanly Acting Rationally
“The art of creating machines “A field of study that seeks to
that perform functions that explain and emulate intelligent
require intelligence when behavior in terms of
performed by people” computational processes”
(Kurzweil, 1990) (Schalkol, 1990)
Artificial Intelligence
Categories of Artificial Intelligence

» Modeling exactly how humans actually think


 cognitive models of human reasoning
» Modeling exactly how humans actually act
 models of human behavior (what they do, not how they think)
» Modeling how ideal agents “should think”
 models of “rational” thought (formal logic)
 note: humans are often not rational!
» Modeling how ideal agents “should act”
 rational actions but not necessarily formal rational reasoning
 i.e., more of a black-box/engineering approach
Artificial Intelligence
ARTIFICIAL INTELLIGENCE SYSTEM

Input
Knowledge Inference
Problem
Base Engine

Artificial Intelligence is the study of how to make


computers do things at which, at the moment, people are
better.

[Rich E. and Knight K. “Artificial Intelligence”, 1991].


Artificial Intelligence
FOUNDATION OF AI
Academic Disciplines
Philosophy Logic, methods of reasoning, mind as physical system, foundations
of learning, language, rationality.

Formal representation and proof, algorithms, computation,


Mathematics
(un)decidability, (in)tractability, probability.

Economics Utility, decision theory, rational economic agents


Neuroscience Neurons as information processing units.
How do people behave, perceive, process Cognitive Science
Psychology information, represent knowledge.

Computer Engineering Building fast computers

Control theory Design systems that maximize an objective function over time

Linguistics Knowledge representation, grammar


AGENT
» Anything that can be viewed as perceiving its environment
through sensors and acting upon that environment through its
effectors to maximize progress towards its goals.
CONCEPT OF RATIONALITY
Rational Agent
o For each possible percept sequence, a rational
agent should select an action that is expected to
maximize its performance measure, given the
evidence provided by the percept sequence and
whatever built-in knowledge the agent has.
SPECIFYING THE TASK
ENVIRONMENT
» PAGE (Percepts, Actions, Goals, Environment)
» Task-specific & specialized:
» well-defined goals and environment
» The notion of an agent is meant to be a tool for
analyzing systems,
 It is not a different hardware or new programming
languages.
SPECIFYING THE TASK
ENVIRONMENT
A Windshield Wiper Agent

» How do we design an agent that can wipe the


windshields? When is it needed?
Goals?
Percepts?
Sensors?
Effectors?
SPECIFYING THE
TASK
A Windshield Wiper Agent
o Goals:
ENVIRONMENT
• Keep windshields clean & maintain visibility
o Percepts:
• Raining, Dirty
o Sensors:
• Camera (moist sensor)
o Effectors:
• Wipers (left, right, back)
o Actions:
• Off, Slow, Medium, Fast
o Environment:
• Inner city, freeways, highways, weather
SPECIFYING THE TASK
Example of Agent Types ENVIRONMENT
Performance
Agent Type Environment Actuators Sensors
Measure
Medical Healthy patient, Patient, hospital, Display of questions, Keyboard entry of
Diagnosis reduced cost staff tests, diagnoses, symptoms, findings,
System treatments, referrals. patient’s, answers.
Satellite image Correct image Downlink from Display of scene Color pixel arrays
analysis categorization orbiting satellite categorization
system
Part-picking Percentage of Conveyor belt Jointed arm and Camera, joint angle
robot part in correct with part; bins hand sensors
bins
Refinery Purity, yield, Refinery, Valves, pumps, Temperature,
controller safety operators heaters, displays pressure, chemical
sensors
Interactive Student’s score Set of students, Display of exercises, Keyboard entry
English tutor on test testing agency suggestions,
corrections
HOW IS AN AGENT
DIFFERENT
» Agents are autonomous,
FROM OTHER that is, they act on
SOFTWARE?
behalf of the user.
(1)
» Agents contain some level of intelligence, from
fixed rules to learning engines that allow them
to adapt to changes in the environment.
» Agents don't only act reactively, but sometimes
also proactively.
HOW IS AN AGENT
» Agents have social ability, that DIFFERENT
is, they
communicate with FROM OTHER
the user, SOFTWARE?
the system, and other
agents as required. (2)
» Agents may also cooperate with other agents to
carry out more complex tasks than they
themselves can handle.
» Agents may migrate from one system to another
to access remote resources or even to meet other
agents.
PROPERTIES OF ENVIRONMENT
• Accessible vs. inaccessible
 Sensors give access to complete state of the environment.
• Deterministic vs. nondeterministic
 The next state can be determined based on the current state and
the action.
• Episodic vs. non-episodic (Sequential)
 Episode: each perceive and action pairs
 The quality of action does not depend on the previous episode.
• Hostile vs. friendly
• Static vs. dynamic
 Dynamic if the environment changes during deliberation
• Discrete vs. continuous
 Chess vs. driving
ENVIRONMENT TYPES
Environ- Determi-
Accessible Episodic Static Discrete
ment nistic
Operating Yes Yes No No Yes
System
Virtual Yes Yes Yes/No No Yes/No
Reality
Office No No No No No
Environment
Mars No Semi No Semi No

The environment types largely determine the agent design


STRUCTURE OF
INTELLIGENCE AGENTS
o Agent = architecture + program

o Agent program: the implementation of f : P*  A, the agent’s


perception-action mapping

function Skeleton-Agent(Percept) returns Action


memory  UpdateMemory(memory, Percept)
Action  ChooseBestAction(memory)
memory  UpdateMemory(memory, Action)
return Action

o Architecture: a device that can execute the agent program (e.g., general-
purpose computer, specialized device, etc.)
AGENT TYPES
o Reflex agents
• Reactive: No memory
o Reflex agents with internal states
• W/o previous state, may not be able to make decision
 e.g. brake lights at night.
o Goal-based agents
• Goal information needed to make decision
o Utility-based agents
• How well can the goal be achieved (degree of happiness) ?
• What to do if there are conflicting goals (speed and
safety) ?
REFLEX AGENTS
REACTIVE AGENTS

o Reactive agents do not have internal symbolic models.


o Act by stimulus-response to the current state of the
environment.
o Each reactive agent is simple and interacts with others in a
basic way.
o Complex patterns of behavior emerge from their interaction.
o Benefits: robustness, fast response time
o Challenges:
• scalability, how intelligent?
• and how do you debug them?
REFLEX AGENTS
WITH STATE
GOAL-BASED AGENTS
UTILITY-BASED AGENTS
SUMMARY
» Artificial Intelligence involves the study of:
• automated recognition and understanding of speech,
images, etc
• learning and adaptation
• reasoning, planning, and decision-making
» AI has made substantial progress in
• recognition and learning
• some planning and reasoning problems
» AI Applications
• improvements in hardware and algorithms => AI
applications in industry, finance, medicine, and
science.
» AI Research
SUMMARY
o Intelligent Agents:
• Anything that can be viewed as perceiving its
environment through sensors and acting upon that
environment through its effectors to maximize
progress towards its goals.
• PAGE (Percepts, Actions, Goals, Environment)
• Described as a Perception (sequence) to Action
Mapping: f : P* A
• Using look-up-table, closed form, etc.
o Agent Types:
Reflex, state-based, goal-based, utility-based
o Rational Action:
The action that maximizes the expected value of the
SOME ARTICLES
1. Applications Of Artificial Intelligence in Food Science
and Technology Area
2. Applications Of Artificial Intelligence in Food
Engineering Research & Industry
3. Integrating Multimedia and Artificial Intelligence
REFERENCES
o Stuart Russell, Peter Norvig,. 2010. Artificial intelligence :
a modern approach. PE. New Jersey.
ISBN:9780132071482, Chapter 3
o Elaine Rich, Kevin Knight, Shivashankar B. Nair. 2010.
Artificial Intelligence. MHE. New York. , Chapter 3
o Some Definitions of "Artificial Intelligence“:
http://www.cse.buffalo.edu/~rapaport/definitions.of.ai.html
o Artificial intelligence And Chess:
http://www.youtube.com/watch?v=4_L1iPEEgoo&feature=
related
ThankYOU...

You might also like