1 Introduction
1 Introduction
Unit 2
Uninformed Search, Sensor less problems, Contingency problems, Heuristic
Search, local search and optimization, online search.
Unit 3
Constraint Satisfaction Problems, Game Theory, Probability basics, Bayesian
Networks, Fuzzy logics, Beliefs, Desires and Uncertainty.
Unit 4
The planning problem, partial order planning, planning graphs and algorithms,
Basics of ANN.
Unit 5
Expert Systems, Logic and knowledge based systems, Semantic Nets.
2
COURSE OBJECTIVE
To learn the difference between optimal reasoning Vs human like reasoning.
To understand the notion of state space representation along with time and space
complexities.
To learn the methods of solving problems using Artificial Intelligence.
To introduce the concepts of machine learning.
Able to work in uncertain environments using probabilistic reasoning
techniques.
3
BOOK PREFERRED
5. Saroj Kaushik, “Logic and Prolog Programming”, New Age International Pvt
Ltd
4
SOME DEFINITIONS (I)
Behaviour
ACTING HUMANLY (TURING
TEST)
12
TURING TEST..RESULT
Ifthe interrogator can not reliably distinguish
the human from the computer.
13
WHAT DOES AI REALLY DO?
Knowledge Representation (how does a program represent
its domain of discourse?)
Automated reasoning.
AI becomes an industry:
configuring computers.
Robotic vision applications
RECENT EVENTS: 1987-PRESENT
AI turns more scientific, relies on more mathematically
sophisticated tools:
Hidden Markov models (for speech recognition)
Belief networks (see Office 97).
Biology
Economics
Neuroscience
Psychology
Control Theory
Linguistic
Computer Science
23
INTELLIGENT BEHAVIOR
Perception
Reasoning
Learning
Understanding Language
Solving Problem
APPLICATIONS
Computer vision
Image recognition
Robotics
NLP
Speech Processing
Machine Translation
Autonomous agents—Mangalyan, Mars Rover
Internet agents
Transportation
Healthcare
E-commerce
TYPES OF AI
WEAK AI
Weak AI
deals with the creation of some form of computer-based artificial
intelligence that cannot truly reason and solve problems, but can act as if
it were intelligent.
Focuses on one narrow task and cannot perform beyond its limitation.
Solving puzzle,
Making judgements
APPLIED AI-
Applied AI
aims to produce commercial viable smart system-such as
for example a security system that is able to recognize
the faces of people who are permitted to enter a
particular building
Applied AI has already enjoyed considerable success.
Example-Recognize people
COGNITIVE AI
Cognitive AI
Computer are used to test theories about how the human
mind works-for example, theories about how we
recognize faces and other objects, or about how we solve
abstract problem.
ARTIFICIAL INTELLIGENCE TYPE-2:
BASED ON FUNCTIONALITY
Reactive Machines
Reactive machines are the most basic types of Artificial Intelligence.
Such AI systems do not store memories or past experiences for future
actions.
These machines only focus on current scenarios and react on it as per
possible best action.
Example:
IBM's Deep Blue
Google's AlphaGo
ARTIFICIAL INTELLIGENCE TYPE-2:
BASED ON FUNCTIONALITY
Limited Memory
Example
Self-driving cars
ARTIFICIAL INTELLIGENCE TYPE-2:
BASED ON FUNCTIONALITY
Theory of Mind
This type of AI machines are still not developed, but researchers are
making lots of efforts and improvement for developing such AI
machines.
ARTIFICIAL INTELLIGENCE TYPE-2:
BASED ON FUNCTIONALITY
Self-Awareness
Self-awareness AI is the future of Artificial Intelligence. These
machines will be super intelligent, and will have their own
consciousness, sentiments, and self-awareness.
AI start-up's in India
https://www.mygreatlearning.com/blog/top-ai-startups-in-india/
35
WHY AI ? AND ITS IMPORTANCE (CONT..
World Wide Competition in AI field
1. Numer.ai
2. Data Analysis Competition 2021 by IASC
3. TopCoder Open 2021
4. Challenge data 2021
5. Kaggle Competitions
6. CodaLab
7. Driven Data
8. DataHack
9. Machine Hack
10. AIcrowd
36
Thank You!!