Unit-1
Introduction to artificial intelligence
Looping
Outline
Introduction to Artificial Intelligence (AI)
The AI Problem
The Underlying Assumption
AI Techniques
The level of model
Criteria for success
Applications of AI
What is Artificial Intelligence (AI)?
AI is the science and
engineering of making
intelligent machines,
especially intelligent
computer programs (1956).
John McCarthy
(the father of Artificial
Intelligence)
AI is a branch of computer science dealing with the simulation of intelligent behavior in
computers.
AI is the study of how to make computers do things which, at the moment, people do better.
AI is, the study and design of intelligent agents where an intelligent agent is a system that
perceives its environment and takes actions.
Acting Humanly: The Turing Test
proposed by Alan Turing (1950)
A Turing Test is a method of inquiry
for determining whether or not a
computer is capable of thinking like
a human being.
The interrogator job is to try and
figure out which one is human and
which one is computer by asking
questions to both of them.
The computer would try to remain
indistinguishable from human as
much as possible
AI Techniques
There are three important AI techniques:
1. Search –
Provides a way of solving problems for which no direct approach is available.
It also provides a framework into which any direct techniques that are available can be embedded.
2. Use of knowledge –
Provides a way of solving complex problems by exploiting the structure of the objects that are involved.
3. Abstraction –
Provides a way of separating important features and variations from many unimportant ones that would
otherwise overwhelm any process.
Task Domains of AI
Mundane tasks Formal tasks Expert tasks
Perception Games Engineering
Computer Vision Go Design
Speech, Voice Chess (Deep Blue) Fault Finding
Ckeckers Manufacturing
Monitoring
Natural Language Mathematics Scientific Analysis
Processing Geometry
Understanding Logic
Language Generation Integration and
Language Translation Differentiation
Common Sense Reasoning Theorem Proving Financial Analysis
Planning Medical Diagnosis
Robot Control
History of AI
APPLICATION DOMAINS OF AI
Natural Language Processing
Email Spam Filter in
Neural Network
Gmail
Image Processing
Face Detection in
Deep Learning
Camera
Speech Recognition
Voice Technology in
Deep Learning
Virtual Agents
Data Mining
Market Basket
Product
Analysis
recommendation
Expert System
IBM Watson Reinforcement Learning
Robotics
Home Automation Deep Learning
Scheduling
Resource Aurora - Advanced
Intelligent Planning and
Scheduling
Scheduling Solution
Optimization
Shortest Path Google map path
planner
Game Playing
Alpha Go Deep Neural Network
Virtual Agents
Chatbots Conversational AI
Personalized Recommender Systems
Online Shopping Machine Learning
Automated Control Systems
Washing Machine Fuzzy Logic
Security
NVIDIA Metropolis Machine Learning
AI – ML – DL and Data Science
Technique that enables
machines to mimic
human behavior
AI
Subset of AI which
Machine uses statistical
Learnin methods to enable
Data g machine to learn and
improve with time
Scienc
e
Deep Subset of ML that
Learnin includes algorithms
and enables system
g
to train itself
THANK YOU!
