2. Unit1:Introduction to AI & ML
2
WHAT IS ARTIFICIAL INTELLIGENCE(AI)?
The word Artificial Intelligence comprises of two words
“Artificial” and “Intelligence”. Artificial refers to something
which is made by humans or non-natural thing and Intelligence
means the ability to understand or think.
AI is the study of how to train the computers so that
computers can do things which at present human can do
better. Therefore, AI is an intelligence where we want to add all
the capabilities to machine that human contains.
3. WHAT IS MACHINE LEARNING(ML)?
3
MACHINE LEARNING is an application of Artificial intelligence in which
machine can automatically learn on its own and improve from
experience without being explicitly programmed.
ML gives computer that which makes it more similar to humans: The
ability to learn.
Machine learning is a subset of AI that focuses on a narrow range of
activities. It is, in fact, the only real artificial intelligence with some
applications in real-world problems.
4. Introduction
• According to the father of Artificial Intelligence, John McCarthy, it is “The
science and engineering of making intelligent machines, especially intelligent
computer programs”. Artificial Intelligence is a way of making a computer, a
computer-controlled robot, or a software think intelligently, in the similar
manner the intelligent humans think
• Machine Learning (ML) is usually considered as a subfield of AI. ML is a data-
driven approach focused on creating algorithms that has the ability to learn from
the data without being explicitly programmed.
• What is the need of AI?
• AI technology is important because it enables human capabilities –understanding,
reasoning, planning, communication and perception – to be undertaken by
software increasingly effectively, efficiently and at low cost. ... Applications of AI-
powered computer vision will be particularly significant in the transport sector.
4
5. AI Definitions
• The study of how to make programs/computers do things that people do
better
• The study of how to make computers solve problems which require knowledge
and intelligence
• The exciting new effort to make computers think … machines with minds
• The automation of activities that we associate with human thinking (e.g.,
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
• A field of study that seeks to explain and emulate intelligent behavior in terms
of computational processes
• The branch of computer science that is concerned with the automation of
Thinking
machines or
machine
intelligence
Studying
cognitive
faculties
Problem
Solving and
CS
6. So What Is AI?
• AI as a field of study
• Computer Science
• Cognitive Science
• Psychology
• Philosophy
• Linguistics
• Neuroscience
• AI is part science, part engineering
• AI often must study other domains in order to implement systems
• e.g., medicine and medical practices for a medical diagnostic system, engineering and
chemistry to monitor a chemical processing plant
• AI is a belief that the brain is a form of biological computer and that the mind is
computational
• AI has had a concrete impact on society but unlike other areas of CS, the impact is
often
• felt only tangentially (that is, people are not aware that system X has AI)
• felt years after the initial investment in the technology
7. What is Intelligence?
• Is there a “holistic” definition for intelligence?
• Here are some definitions:
• the ability to comprehend; to understand and profit from experience
• a general mental capability that involves the ability to reason, plan, solve problems, think
abstractly, comprehend ideas and language, and learn
• is effectively perceiving, interpreting and responding to the environment
• None of these tells us what intelligence is, so instead, maybe we can enumerate a
list of elements that an intelligence must be able to perform:
• perceive, reason and infer, solve problems, learn and adapt, apply common sense, apply
analogy, recall, apply intuition, reach emotional states, achieve self-awareness
• Which of these are necessary for intelligence? Which are sufficient?
• Artificial Intelligence – should we define this in terms of human intelligence?
• does AI have to really be intelligent?
• what is the difference between being intelligent and demonstrating intelligent behavior?
8. History of AI
• [1943-1955] The gestation of artificial intelligence ,McCulloch & Pitts: model of artificial neurons
• Two undergraduate students at Harvard, Marvin Minsky and Dean Edmonds, built the first neural
network computer in 1950.
• Alan Turing gave lectures on the topic as early as 1947 at the London Mathematical Society and
articulated a persuasive agenda in his 1950 article "Computing Machinery and Intelligence.
• [1956] The birth of artificial intelligence John McCarthy moved to Dartmouth College. He
convinced Minsky, Claude Shannon, and Nathaniel Rochester to help him bring together
U.S. researchers interested in automata theory, neural nets, and the study of intelligence.
• [1952-1969] Early enthusiasm, great expectations of General Problem Solver (GPS). This
program was designed from the start to imitate human problem-solving protocols. Within
the limited class of puzzles it could handle, it turned out that the order in which the
program considered sub goals and possible actions was similar to that in which humans
approached the same problems.
8
9. History of AI
• [1966-1973] A dose of reality ○ Simon stated that within 10 years a computer would be
chess champion, and a significant mathematical theorem would be proved by machine.
• [1974-1980] First AI winter ○ (1966), a report by an advisory committee found that "there
has been no machine translation of general scientific text, and none is in immediate
prospect." All U.S. government funding for academic translation projects was canceled.
• [1980-present] AI becomes an industry ○ The first successful commercial expert system,
RI, began operation at the Digital Equipment Corporation (McDermott, 1982).
• [2001-present] The availability of very large data sets ○ Throughout the 60-year history of
computer science, the emphasis has been on the algorithm as the main subject of study.
But some recent work in Al suggests that for many problems, it makes more sense to
worry about the data and be less picky about what algorithm to apply.
9
10. A Brief History of AI: 1950s
• Computers were thought of as an electronic brains
• Term “Artificial Intelligence” coined by John McCarthy
• John McCarthy also created Lisp in the late 1950s
• Alan Turing defines intelligence as passing the Imitation
Game (Turing Test)
• AI research largely revolves around toy domains
• Computers of the era didn’t have enough power or memory to
solve useful problems
• Problems being researched include
• games (e.g., checkers)
• primitive machine translation
• blocks world (planning and natural language understanding within the
toy domain)
• early neural networks researched: the perceptron
• automated theorem proving and mathematics problem solving
11. The 1960s
• AI attempts to move beyond toy domains
• Syntactic knowledge alone does not work, domain
knowledge required
• Early machine translation could translate English to Russian (“the
spirit is willing but the flesh is weak” becomes “the vodka is good
but the meat is spoiled”)
• Earliest expert system created: Dendral
• Perceptron research comes to a grinding halt when it is
proved that a perceptron cannot learn the X OR operator
• US sponsored research into AI targets specific areas – not
including machine translation
• Weizenbaum creates Eliza to demonstrate the futility of AI
12. 1970s
• AI researchers address real-world problems and solutions through
expert (knowledge-based) systems
• Medical diagnosis
• Speech recognition
• Planning
• Design
• Uncertainty handling implemented
• Fuzzy logic
• Certainty factors
• Bayesian probabilities
• AI begins to get noticed due to these successes
• AI research increased
• AI labs sprouting up everywhere
• AI shells (tools) created
• AI machines available for Lisp programming
• Criticism: AI systems are too brittle, AI systems take too much time
and effort to create, AI systems do not learn
13. 1980s: AI Winter
• Funding dries up leading to the AI Winter
• Too many expectations were not met
• Expert systems took too long to develop, too much money to
invest, the results did not pay off
• Neural Networks to the rescue!
• Expert systems took programming, and took dozens of man-
years of efforts to develop, but if we could get the computer
to learn how to solve the problem…
• Multi-layered back-propagation networks got around the
problems of perceptrons
• Neural network research heavily funded because it promised
to solve the problems that symbolic AI could not
• By 1990, funding for neural network research was
slowly disappearing as well
• Neural networks had their own problems and largely could
not solve a majority of the AI problems being investigated
• Panic! How can AI continue without funding?
14. 1990s: A Life
• The dumbest smart thing you can do is staying alive
• We start over – lets not create intelligence, lets just create
“life” and slowly build towards intelligence
• Alife is the lower bound of AI
• Alife includes
• evolutionary learning techniques (genetic algorithms)
• artificial neural networks for additional forms of learning
• perception and motor control
• adaptive systems
• modeling the environment
• Let’s disguise AI as something new, maybe we’ll get
some funding that way!
• Problems: genetic algorithms are useful in solving some
optimization problems and some search-based problems, but
not very useful for expert problems
• perceptual problems are among the most difficult being
solved, very slow progress
15. Today: The New (Old) AI
• Look around, who is doing AI research?
• By their own admission, AI researchers are not doing “AI”, they are
doing
• Intelligent agents, multi-agent systems/collaboration
• Ontologies
• Machine learning and data mining
• Adaptive and perceptual systems
• Robotics, path planning
• Search engines, filtering, recommendation systems
• Areas of current research interest:
• NLU/Information Retrieval, Speech Recognition
• Planning/Design, Diagnosis/Interpretation
• Sensor Interpretation, Perception, Visual Understanding
• Robotics
• Approaches
• Knowledge-based
• Ontologies
• Probabilistic (HMM, Bayesian Nets)
• Neural Networks, Fuzzy Logic, Genetic Algorithms
16. Brain vs. Computer
• In AI, we compare the brain (or the mind) and the
computer
• Our hope: the brain is a form of computer
• Our goal: we can create computer intelligence through
programming just as people become intelligent by learning
But we see that the computer
is not like the brain
The computer performs tasks
without understanding what
its doing
Does the brain understand
what its doing when it solves
problems?
17. Comparison of Artificial Intelligence and Data
Science
• Data Science is a
comprehensive process that
involves pre-processing,
analysis, visualization and
prediction.
• On the other hand, AI is
the implementation of a
predictive model to forecast
future events.
• Data Science comprises of
various statistical techniques
whereas AI makes use of
computer algorithms.
17
18. Need of AI in Mechanical Engineering
• It can be termed as Machine intelligence.
• It combines a wide variety of advanced technologies to give machine
the ability to learn, adapt, make decisions and display behaviors not
explicitly programmed into their original capabilities.
• Different Areas: Robotics, Speech Recognition, Facial Recognition,
navigation mapping, motion, planning, and object recognition.
• Mechanical engineers with AI skills would be required to work on
software which can handle data provided by sensors in components
of power plant, production facility or consumer products. ... Data
collected from Supervisory Control And Data Acquisition (SCADA) can
help predict failures, avoiding any loss of money or life.
18
19. Introduction to Machine Learning
• Machine learning is making great strides
• Large, good data sets
• Compute power
• Progress in algorithms
• Many interesting applications
• commericial
• scientific
• Links with artificial intelligence
• However, AI machine learning
19
20. What are the 5 components of AI
• Research in AI has focused chiefly on the following components of
intelligence: learning, reasoning, problem-solving, perception, and
language-understanding.
• Learning. Learning is distinguished into a number of different forms. ...
• Learning is one of the fundamental building blocks of artificial intelligence (AI) solutions.
• From a conceptual standpoint, learning is a process that improves the knowledge of an
AI program by making observations about its environment.
• Reasoning.
• Problem-solving.
• Perception.
• Language-understanding.
20
21. • Reasoning: plays a great role in the process of artificial Intelligence. Thus Reasoning can be
defined as the logical process of drawing conclusions, making predictions or constructing
approaches towards a particular thought with the help of existing knowledge.
• Problem Solving: In Artificial Intelligence, the users can solve the problem by performing
logical algorithms, utilizing polynomial and differential equations, and executing them using
modeling paradigms. There can be various solutions to a single problem, which are achieved by
different heuristics.
• Knowledge: Representation and reasoning is the field of artificial intelligence (AI) dedicated to
representing information about the world in a form that a computer system can use to solve
complex tasks such as diagnosing a medical condition or having a dialog in a natural language.
• Planning: in Artificial Intelligence is about the decision making tasks performed by the robots
or computer programs to achieve a specific goal. The execution of planning is about choosing
a sequence of actions with a high likelihood to complete the specific task
• Perception: in Artificial Intelligence is the process of interpreting vision, sounds, smell, and
touch. Perception helps to build machines or robots that react like humans. ... The main
difference between AI and robot is that the robot makes actions in the real world.
• Motion: AI is improving robotic motion tasks by breaking down individual joint movements
into motion primitives or sequences of movement. ... For example, when motors and drives
are in upper-level control, AI can respond to and manipulate uncommon changes in real time.
• Manipulation: Will artificial intelligence one day be able to use our cognitive biases against ...
including the possibility of AI that may one day be able to manipulate
21
22. Approaches to AI
• Cybernetics and brain simulation
• Cybernetics and artificial intelligence (AI) are often considered the same thing, with cybernetics
having something to do with creating intelligent cyborgs and robots. ... Cybernetics more broadly
encompasses the study of how systems regulate themselves and take action toward goals based
on feedback from the environment.
• Symbolic
• In the Symbolic approach, AI applications process strings of characters that represent real-world
entities or concepts. Symbols can be arranged in structures such as lists, hierarchies, or networks
and these structures show how symbols relate to each other.
• Sub-symbolic
• Implicit representation is derived from the learning from experience with no symbolic
representation of rules and properties. The main assumption of the subsymbolic paradigm is that
the ability to extract a good model with limited experience makes a model successful.
• Statistical
• It's a process where the AI system gather, organize, analyze and interpret numerical information
from data. More and more industries are applying AL to process improvement in the design and
manufacture of their products. 22
23. Approaches to ML
• Supervised learning
• regression: predict numerical values
• classification: predict categorical values, i.e., labels
• Unsupervised learning
• clustering: group data according to "distance"
• association: find frequent co-occurrences
• link prediction: discover relationships in data
• data reduction: project features to fewer features
• Reinforcement learning
• Reinforcement learning is the training of machine learning models to make a sequence
of decisions.
• To get the machine to do what the programmer wants, the artificial intelligence gets
either rewards or penalties for the actions it performs. Its goal is to maximize the total
reward. 23
24. Text Books
• 1. Deisenroth, Faisal, Ong, Mathematics for Machine Learning,
Cambridge University Press, 2020.
• 2. B Joshi, Machine Learning and Artificial Intelligence, Springer, 2020.
• 3. Parag Kulkarni and Prachi Joshi, “Artificial Intelligence – Building
Intelligent Systems”, PHI learning Pvt. Ltd., ISBN – 978-81-203-5046-5,
2015
• 4. Stuart Russell and Peter Norvig (1995), “Artificial Intelligence: A
Modern Approach,” Third edition, Pearson, 200
24
25. References Books
• 1. Solanki, Kumar, Nayyar, Emerging Trends and Applications of
Machine Learning, IGI Global, 2018.
• 2. Mohri, Rostamizdeh, Talwalkar, Foundations of Machine Learning,
MIT Press, 2018.
• 3. Kumar, Zindani, Davim, Artificial Intelligence in Mechanical and
Industrial Engineering, CRC Press, 2021.
• 4. Zsolt Nagy - Artificial Intelligence and Machine Learning
Fundamentals-Apress (2018)
• 5. Artificial Intelligence by Elaine Rich, Kevin Knight and Nair, TMH
25