Professional Documents
Culture Documents
INTELLIGENCE
PRESENTED BY:
MS. SUMITA LAMBA
ASSISTANT PROFESSOR (Sr.)
DEPARTMENT OF AIML
ABESEC
Goals of the course
•To introduce you to the field of AI.
02 What is Intelligent
System?
03 Approaches to AI
Artificial: Made by
humans or man made.
Intelligence: Ability to
think, understand and World's "First Robot Citizen" Talks About Climate
learn. Change On India Visit
Artificial Intelligence
ARTIFICIAL INTELLIGENCE
Term coined by McCarthy in 1956.
Concerned with design of intelligence in an artificial device
What is intelligence?
Humans?
Behave as intelligently as a human
Behave in ideal way or in the best possible manner (Behavior)
a. Thinking: thinking intelligently, reasoning properly in order to
come up with a solution
b. Acting: How the system acts or behaves
Intelligent
data in similar manner as humans.
Learning
A process of acquiring new understandings,
knowledge, skills and preferences.
Reasoning
Capability of thinking about something in a
logical, sensible way.
From where it
all began!
Early History
A very brief history of AI
1969 2002
1950 Shakey
The debut of
Roomba
Turing Test This was the first
"Computing Machinery general purpose mobile An autonomous robotic
and Intelligence.“ robot build. vacuum cleaner.
1972- WaBot-1
1956 1997
Emergence of
2005-20
Birth of AI
Intelligent Agents Age of AI
The word “Artificial
Intelligence” coined by IBM’s Super Computer Siri by Apple in iphone 4s
John McCarthy. “DEEP BLUE” was (2011), Speech
1966: ELIZA designed which defeated recognition, dancing
the world chess robot.
champion in a game.
Table of Contents
Actuators: Actuators are the component of machines that converts energy into motion.
The actuators are only responsible for moving and controlling a system.
•Have goals
What can be identified as Agent?
Human-Agent: A human agent has sensory organs like eyes, ears, skin, etc for
sensing from environment and organs like hand, legs, vocal tract work for actuators
and effectors.
Robot Agent: A robotic agent can have cameras, sonar sensors infrared range finder,
NLP for sensors and various motors, grippers, wheels, lights, speakers for actuators
and effectors.
Software Agent (Soft bots): Software agent can have keystrokes, file contents as
sensory input and act on those inputs and display output on the screen. E.g.: Expert
System.
Intelligent Agents
•An autonomous entity which act upon an environment using sensors and actuators for
achieving goals.
•It must decide autonomously what action to take in the current situation to maximize
progress towards its goal.
•An intelligent agent may learn from the environment to achieve their goals.
AI is about creating rational agents to use for game theory and decision theory for
various real-world scenarios.
f:P* → A
Agent program: Agent program is an implementation of agent function.
PEAS Representation Model
P: Performance measure
E: Environment
A: Actuators
S: Sensors
PEAS of Vacuum cleaner
Performance: Cleanliness and efficiency
3. Part -picking •Percentage of parts in •Conveyor belt with •Jointed Arms •Camera
Robot correct bins. parts, •Hand •Joint angle sensors.
•Bins
Types of Agents in Artificial Intelligence
1. Reflex Agents: They choose actions only based on the current percept. Environment is completely
observable.
Condition-Action Rule − maps a state (condition) to an action.
2. Model Reflex Agents: Use a model of the world to choose their actions. They maintain an internal
state.
Types of Agents
3. Goal-based agents: They choose their actions in order to achieve goals. Goal-based
agents expand the capabilities of the model-based agent by having the "goal"
information. Works on searching and planning.
4. Utility-based agents: Utility-based agent act based not only goals but also the best
way to achieve the goal. Checks for the state of the agent after each action.