Machine learning and artificial intelligence solutions

1
DISCOVER . LEARN . EMPOWER
UNIVERSITY INSTITUTE OF
ENGINEERING
DEPARTMENT OF COMPUTER SCIENCE
AND ENGG.
Bachelor of Engineering (Computer Science & Engineering)
Artificial Intelligence and Machine Learning(21CSH-316)
Prepared by:
Sitaram patel(E13285)
Chapter-1.1 Lecture-1
www.cuchd.in Computer Science and Engineering Department

AI
Creating Machine
with
Intelligence

COURSE OUTCOMES
3
CO1-Understand the fundamental concepts and
techniques of artificial intelligence and machine
learning.
CO2- Apply the basic of python programming to
various problems related to AI

COURSE OBJECTIVES
4
To make familiar with the domain and
fundamentals of Artificial intelligence.
To provide a
comprehensive foundation
to Machine Learning and
Optimization methodology
with applications t.
To study learning processes:
supervised and unsupervised,
deterministic and statistical
knowledge of Machine learners,
and ensemble learning
To understand modern
techniques and practical trends
of Machine learning.

SYLLABUS
UNIT-I
Chapter-1
Concept of AI, history, current status, scope, agents, environments, Problem
Formulations, Review of tree and graph structures, State space representation,
Search graph and Search tree.
5

AREAS OF AI AND SOME
DEPENDENCIES
Search
Vision
Planning
Machine Learning
Knowledge Representation
Logic
Expert Systems
Robotics
NLP

WHAT IS ARTIFICIAL INTELLIGENCE ?
 making computers that think?
 the automation of activities we associate with human thinking, like decision
making, learning ... ?
 the art of creating machines that perform functions that require intelligence
when performed by people ?
 the study of mental faculties through the use of computational models ?

 the study of computations that make it possible to perceive, reason and
act ?
 a field of study that seeks to explain and emulate intelligent behaviour
in terms of computational processes ?
 a branch of computer science that is concerned with the automation of
intelligent behaviour ?
 anything in Computing Science that we don't yet know how to do
properly ? (!)

Systems that act
rationally
Systems that think
like humans
Systems that think
rationally
Systems that act
like humans
THOUGHT
BEHAVIOUR
HUMAN RATIONAL

GOALS OF AI
 To make computers more useful by letting them take over dangerous or tedious
tasks from human
 Understand principles of human intelligence

11
AI AGENTS & ENVIRONMENTS
-
 An AI system is composed of an agent and its environment.The agents act in their
environment.The environment may contain other agents.
What are Agent and Environment?
 An agent is anything that can perceive its environment through sensors and acts upon that
environment through effectors.
 A human agent has sensory organs such as eyes, ears, nose, tongue and skin parallel to the
sensors, and other organs such as hands, legs, mouth, for effectors.
 A robotic agent replaces cameras and infrared range finders for the sensors, and various
motors and actuators for effectors.
 A software agent has encoded bit strings as its programs and actions.

CONT
 Agent Terminology
 Performance Measure of Agent It is the criteria, which determines how
−
successful an agent is.
 Behavior of Agent It is the action that agent performs after any given
−
sequence of percepts.
 Percept It is agent’s perceptual inputs at a given instance.
−
 Percept Sequence It is the history of all that an agent has perceived till date.
−
 Agent Function It is a map from the precept sequence to an action.
−
Scope of AI (AI Careers)
Fresher's should analyze their competencies and skills and choose a better AI
role with the potential for upward mobility.The future scope of Artificial
Intelligence continues to grow due to new job roles and advancements in the AI
field.The various roles in an AI career are as follows:

SCOPE OF AI (AI CAREERS)
 AI Analysts and Developers
 AI Engineer and Scientist
 AI researcher
 AI Algorithms Expert
 Robotics specialist
 Military and aviation specialist
 Maintenance and mechanical engineer
 Surgical AI technician
 The future of AI
 The future of Artificial Intelligence is bright in India, with many organizations opting for AI automation. It is
essential to understand the recent developments in AI to find suitable job roles based on your competencies.
The scope of Artificial Intelligence is limited to domestic and commercial purposes as the medical and aviation
sectors are also using AI to improve their services. If AI is outperforming human efforts, then opting for AI
automation will reduce costs in the long run for a business.
Automation in operational vehicles has created a buzz in the logistics industry as it is expected that
automated trucks/vehicles may soon be used.

14
HISTORY OF ARTIFICIAL INTELLIGENCE
 Myths –Greek Gaint Bronze warrior ‘Talos’
 1950- Alan Turing Proposed the popular ‘Turing Test’
 1951- The year of ‘Game AI’
 1956- John McCarthy coined the term ‘Artificial Intelligence’ at Dartmouth Conference
 1959-First AI Laboratory ‘MIT Lab’ established
 1960-First Robot introduced to the general motors assembly line
 1961-First Chatbot ‘Eliza’ invented
 1997-IBM’s Deep Blue beat World Chess Champion
 2005-Robotic car Stanley won DARPA grand challenge
 2011- IBM’s Watson

15
DEMAND OF AI
 More Computation Power(advanced technology, GPUs)
 Big Data(Enormous data generated from all possible sources)
 Better Algorithms(new efficient algorithms based on neural networks, deep
learning)
 Popularity among Tech Gaints(Universities, Governments, Startups and leading IT
companies like Google, Microsoft, Facebook investing in AI)

16
ARTIFICIAL INTELLIGENCE
 The term AI was first coined in the year 1956 by John McCarthy at Dartmouth
Conference.
 He defined AI as the science and engineering of making intelligent machines.
 AI can be defined as the theory and development of computer systems to be able
to perform task that normally require human intelligence.

SEARCH ALGORITHMS
 Search algorithms differ by the order in which they visit (reach) the states in
the state graph following the edges between them. For some algorithms, that
order creates a tree superimposed over the state graph and whose root is the start
state.We call that tree a search tree and will consider only the algorithms that grow
it.But, how do we grow a search tree in those algorithms? Whenever we reach a
state, we create a node we mark with that state. Later, we insert the node into the
tree as a child of the node from whose state we reached it.
 We see the differences between the states in the state graph and nodes in the
search tree. Each state appears in the graph only once. But, it may appear in the
tree multiple times. That’s because, in the general case, there may be more than
one path from the start state to any other state in the graph. So, different search-
tree nodes marked with the same state represent different paths from the start
to that state.
 There lies the difference between the tree-like and the graph search
strategies.The latter avoids repeating the states in the search tree.

SEARCH GRAPH
 Graph search by AI refers to the process of using artificial intelligence techniques to search
and navigate through a graph data structure. A graph consists of nodes (vertices) and edges
that connect these nodes. Graph search algorithms aim to find specific nodes or paths within a
graph based on certain criteria.
 AI-powered graph search algorithms leverage techniques such as heuristic search, depth-first
search, breadth-first search, A* search, or other optimization methods to efficiently explore the
graph.These algorithms can be used in various domains, including computer science, data
analysis, recommendation systems, natural language processing, and more.
 By employing AI in graph search, algorithms can intelligently traverse the graph, evaluating
nodes and edges based on predefined rules or learned patterns.This allows for efficient
navigation, problem-solving, and decision-making within complex and interconnected data
structures. AI-powered graph search can be particularly useful in scenarios where traditional
search algorithms may be inefficient or impractical due to the size or complexity of the graph.

AI-APPLICATION

 more powerful and more useful computers
 new and improved interfaces
 solving new problems
 better handling of information
 relieves information overload
 conversion of information into knowledge
Some Advantages of Artificial Intelligence

THE DISADVANTAGES
 increased costs
 difficulty with software development - slow and expensive
 few experienced programmers
 few practical products have reached the market as yet.

USEFUL RESOURCES
TEXT BOOKS:
 Rich E., Artificial Intelligence,Tata McGraw Hills.
 George F. Luger, Artificial Intelligence: Structures and Strategies for Complex Problem Solving,
Pearson Education Asia.
REFERENCE BOOKS:
 D.W.Patterson, Introduction to AI and Expert Systems, PHI.
 N.J.Nilsson, Principles of Artificial Intelligence, Kaufmann,1980
 Saroj Kaushik,Logic and Prolog Programming, New Age International Publications.
 PH.Winston,Artificial Intelligence, Addison Wesley.

THANK YOU
For queries
Email: jasneete7747@cumail.in
25

Machine learning and artificial intelligence solutions

More Related Content

Similar to Machine learning and artificial intelligence solutions (20)

Recently uploaded (20)

Machine learning and artificial intelligence solutions