INTRODUCTION TO ARTIFICIAL

INTELLIGENCE
 INTRODUCTION
• Artificial + Intelligence
( Human made things) + (Ability to understand, think and learn)
• Artificial Intelligence(AI) can be defined as an approach of
creating an automatic robot, or a system ,or a software, having
intelligence same as humans and perform task with the same
efficiency as human do.
• John McCarthy first coined term AI in year 1956.
• John McCarthy defined AI as science and Engineering of
making intelligent machine which can behave like a human,
think like a human and able to make decision.
• In simple words AI means machine as “Having its own intelligence”
• AI solve hard problems for which we don’t have good algorithms
e. g., understanding spoken natural language, medical diagnosis,
circuit design, learning, self-adaptation, reasoning, chess playing,
proving math theories, etc.
 Concept of Artificial Intelligence
• Artificial Intelligence is an area of computer science that
emphasizes the creation of intelligent machines that work and
reacts like humans.
• Artificial Intelligence is built on three important concepts:
1. Machine Learning:
• Machine learning uses algorithms to parse data, learn from that
data and make informed decisions based on what it has learned.
2.Deep Learning:
• Deep learning structures algorithms in layers to create an
artificial neural networks that can learn and make intelligent
decisions on its own.
3.Neural Network:
• Neural network consists of computer program that mimic the way
human brain process information.
 WHY AI ?
• With the help of AI, we can create such software or device
which can solve real world problems very easily and accurately
such as health issue, Marketing, traffic issues.
• With the help of AI ,we can create personal virtual assistant
such as Goggle Assistant , Apple Siri, Amazon Alexa etc.
• With the help of AI , we can build robot which can work in
environment where survival of human can be at risk.
• AI opens a path for new technology, new devices and new
opportunities.
 INTELLIGENCE
• Intelligence is the process or part of the power to attain goal
within the world.
• Intelligence is employed to resolve issues or solve problems.
• Intelligence requires ability to sense the environment, to make
decisions and to control actions.
• To begin the discussion, initially we would discuss what is
normally a problem and way it is solved.
 PROBLEM
• Problem is an obstacle that makes it difficult to attain a desired
goal , objective, or purpose.
• It is state of affairs , condition , or issue that is however unresolved
• Each problem has an answer or solution.

SOLUTION
• Procedure that makes the problem navigation towards the goal is
called solution .
• It can be algorithm or a hard –core Implementation to achieve the
goal defined by the problem.
 TYPES OF PROBLEMS AND SOLUTION
1. Structured problems:
• Structured problems for which there exists a specific algorithm to
achieve the goal .
• the same algorithm is run against variety input data still giving a guarantee
of the problem being solved.
• For example: find shortest path using Prim’s algorithm is a structured
problem.
2.Unstructured problems:
• Unstructured problems for which there does not exists a specific
algorithm to achieve the goal .
• What step to take to achieve the goal depends on what is the current state of
problem.
• For example : a problem of playing chess or a problem to write a program to
perform heart surgery of patient are unstructured problems.
• AI is an attempt to make a computer to solve unstructured problems.
 BRANCHES OF AI
• Machine Learning
• Deep Learning
• Neural Network
• Automated Programming
• Robotics
• Expert System
• Natural Language Processing(NLP)
• Computer Vision
• Speech Recognition
• Gaming
 Applications of AI
• Game playing- IBM’s Deep Blue defeated the world chess
champion Garry Kasparov in 1997.
• Mathematics- Proved a mathematical conjecture(Robbins
conjecture) unsolved for decades.
• Diagnosis – Medical diagnosis program able to perform at the level
of an expert physician in several areas of medicine.
• Language understanding and problem solving – Proverb is a
computer program that solves crossword puzzles better than most
humans.
• Robotics- Many surgeons now use robot assistance like (HipNav)
in micro surgery.
• Speech recognition- Speech recognition transform humans speech
into format useful for computer applications , which is used in
interactive voice response systems and mobile application
Applications of AI
• Biometrics-Biometrics is bridge between human and
machine which is not only using image or touch
characteristics but also involves speech and other human
body part recognitions.
• Robotic process automation-AI is also used to create the
automated machine which works same as human and also
supports in many business functions.
• Expert systems-it is a software which uses database of
expert knowledge to offer advise or guide to user.
• Gmail-emails are stored into folders like primary, social ,
promotions and spams using AI program
• Self driving cars-
 Applications of AI
• Finance sector: JP Morgan chases contract intelligent platform uses
AI ,Machine learning and Image Recognition software to analyze legal
documents.
• Manually reviewing 12000 agreements takes over 36,000 hours but AI was
able to do this in a matter of seconds.
• Healthcare: Healthcare organizations uses IBM Watson AI for medical
diagnosis.
• Google's AI eye doctor can examine retina scans & Identify a condition called
diabetic retinopathy which causes blindness.
• Social media: Facebook uses AI for face verification & Machine learning and
Deep learning concept used to detect facial features & Tag your friends.
• Twitter uses AI for Identifying hate speech and terroristic language in tweets.
• It uses Machine learning, deep learning and NLP to filter out offensive
contents.
• The Company discovered and banned 300,000 terrorist linked accounts.
• Google search:
• Virtual Assistants: e.g- Apple-Siri, Amazon-Alexa, Google–Google
Assistant ,Microsoft-Cortana
 Scope of Artificial Intelligence
• The ultimate goal of artificial intelligence is to create computer
programs that can solve problems and achieve goals like humans
would.
• There is scope in developing machines in robotics, computer vision,
language detection machine, game playing, expert systems, speech
recognition machine and much more.
• The following factors characterize a career in artificial
intelligence:
• Automation
• Robotics
• The use of sophisticated computer software
• Individuals considering pursuing a career in this field require specific
education based on the foundations of math, technology, logic and
engineering perspectives. Apart from these, good communication
skills (written and verbal) are imperative to convey how AI services
and tools will help when employed within industry settings.
 AI Approach :
• The difference between machine and human
intelligence is that the human think/act rationally
compare to machine.
• There are four different AI approaches:
1 .Think Well:
• Rational Agent-is a model that can think and learn
like a human.
2.Act Well:
• Heuristic System- solve problem using practical
method.(i.e . trial and error method)
3. Think like humans: Cognitive science approach
• GPS(General Problem Solver) –it solves problem by
following same steps that are followed by human.
4.Act like humans : Behaviorist approach
• Eliza- is a psychotherapist interact with patients and
successfully passed turing test .
Components of AI
Three Dimensional Model of AI
Components of AI
• In AI, the intelligence is intangible which is composed of
mainly five techniques as follows −
• Reasoning
• Learning
• Perception
• Problem Solving
• Linguistic Intelligence
 Components of AI
• Reasoning − It is logical thinking about a problem which is
basis for judgment, advise, decision making and prediction.
• There are broadly two types −

Inductive Reasoning Deductive Reasoning

It starts with a general statement and
It conducts specific observations to examines the possibilities to reach a
makes broad general statements. specific, logical conclusion.

Example − "All women of age above 60

Example − "Nita is a teacher. years are grandmothers.
Nita is studious. Shalini is 65 years.
Therefore, All teachers are studious." Therefore, Shalini is a grandmother."
 Components of AI
• Learning − It is the process of gaining knowledge or skill by
studying, practicing, being taught, or experiencing.
• Perception − It is the process of acquiring, interpreting, selecting,
and organizing sensory information.
• Human being acquires information with the help of sensory organs
like eyes , ears ,nose, etc.
• Similarly AI machines acquires information with the help of different
sensors.
• Problem Solving − It is the process of solving problems , in which
one perceives and tries to arrive at a desired solution from a present
situation by taking some path.
• Problem solving also includes decision making, which is the process
of selecting the best possible path(alternative) for problem solving.
• Linguistic Intelligence − It is the ability to use, speak and write in a
particular language. It is important for interpersonal communication.
 Types of Artificial Intelligence:
• Artificial Intelligence can be divided in various types, there are
mainly two types of main categorization which are based on
capabilities and based on functionally of AI.
 AI type-1: Based on Capabilities
1. Weak AI or Narrow AI:
• Narrow AI is a type of AI which is able to perform a dedicated(Specific) task
with intelligence.
• The most common and currently available AI is Narrow AI in the world of
Artificial Intelligence.
• Narrow AI cannot perform beyond its field or limitations, as it is only trained
for one specific task. Hence it is also termed as weak AI. Narrow AI can fail in
unpredictable ways if it goes beyond its limits.
• Narrow AI can perform limited pre-defined functions.
• Some Example of Narrow AI are:
• Apple-Siri
• Amazon-Alexa
• Google–Google Assistant.
• Face verification in iPhone
• Sophia Robot
• Google Map
• Autopilot feature at Tesla
• playing chess
 AI type-1: Based on Capabilities
2. General AI:
• General AI is a type of intelligence which could perform any
intellectual task with efficiency like a human.
• The idea behind the general AI to make such a system which
could be smarter and think like a human by its own.
• Currently, there is no such system exist which could come under
general AI and can perform any task as perfect as a human.
• The worldwide researchers are now focused on developing
machines with General AI.
• As systems with general AI are still under research, and it will take
lots of efforts and time to develop such systems.
 AI type-1: Based on Capabilities
3. Super AI:
• Super AI is a level of Intelligence of Systems at which machines
could surpass human intelligence, and can perform any task better
than human with cognitive properties. It is an outcome of general
AI.
• Some key characteristics of strong AI include capability include the
ability to think, to reason, solve the puzzle, make judgments, plan,
learn, and communicate by its own.
• Super AI is still a hypothetical concept of Artificial Intelligence.
Development of such systems in real is still world changing task.
AI type-1: Based on Capabilities
 AI type-2: Based on functionality
1. Reactive Machines
• Purely 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.
• IBM's Deep Blue system is an example of reactive machines.
• Google's AlphaGo is also an example of reactive machines.

2. Limited Memory
• Limited memory machines can store past experiences or some data for a
short period of time.
• Self-driving cars are one of the best examples of Limited Memory systems.
These cars can store recent speed of nearby cars, the distance of other cars,
speed limit, and other information to navigate the road.
 AI type-2: Based on functionality
3. Theory of Mind
• Theory of Mind AI should understand the human emotions,
people, beliefs, and be able to interact socially like humans.
• This type of AI machines are still not developed, but researchers are
making lots of efforts and improvement for developing such AI
machines.
4. 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.
• These machines will be smarter than human mind.
• Self-Awareness AI does not exist in reality still and it is a
hypothetical concept.
 Programing languages for AI
• Python:
• Python is considered to be in the first place in the list of all AI
development languages due to the simplicity.
• The syntaxes belonging to python are very simple and can be
easily learn.
• AI algorithms and machine learning algorithms can be easily
implemented in python because it provides lot of predefined
libraries.
• Python takes short development time in comparison to other
languages like Java, C++
• Python supports procedure oriented programming and object
oriented programming features.
• Python is open source language.
 Programing languages for AI
• R:
• It is statistical programing language.
• It is easy to learn ,syntaxes are similar with English language.
• It has also predefined function for machine learning Algorithms,NLP and
so on.
• Java :
• Java can also be considered as a good choice for AI development.
• Artificial intelligence has lot to do with search algorithms, artificial neural
networks and genetic programming.
• Java provides many benefits: easy use, debugging ease, package services,
simplified work with large-scale projects, graphical representation of data
and better user interaction
• LISP:
• It is oldest and most suitable language for AI.
• It is invented by John McCarthy who is also known as father of AI in 1958.
• It is also known for its excellent prototyping capabilities and easy dynamic
creation of new objects, with automatic garbage collection.
 Programing languages for AI
• Prolog:
• This language stays alongside Lisp when we talk about
development in AI field.
• The features provided by it include efficient pattern matching, tree-
based data structuring and automatic backtracking.
• All these features provide a surprisingly powerful and flexible
programming framework.
• Prolog is widely used for working on medical projects and also for
designing expert AI systems.
• Matlab:
• It is mostly used for graphical representation of data.
• C++
• JavaScript
 Machine learning
• Machine Learning is a subset of Artificial Intelligence which
provides machines ability to learn automatically from data and improve
from experience without being explicitly programmed.
• . The term machine learning was first introduced by Arthur
Samuel in 1959.
• Machine Learning consists machine learning algorithms that take input
data, machine learn from that data and make informed decisions based
on what it has learned.
 Machine learning
• In simple terms, Machine Learning means we can feed lot of data to
machine, make machine learn from that data and take its own decisions.
• If we feed good amount of data to machine then machine will
interpret ,analyze data using machine learning algorithms and it will help
us to solve real world problems.
• Currently, Machine Learning used in :
• Self-driving cars,
• Cyber fraud detection,
• Face recognition,
• Speech recognition,
• Email filtering,
• Facebook auto-tagging,
• Recommender system, and many more.
• Various top companies such as Netflix and Amazon have build
machine learning models that are using a vast amount of data to
analyze the user interest and recommend product accordingly.
 Need of Machine Learning
• The need of machine learning is increasing day by day. The reason behind the
need for machine learning is that it is capable of doing tasks that are too
complex for a person to implement directly.
• As a human, we have some limitations, we cannot access the huge amount of
data manually, so for this, we need some computer systems and here comes the
machine learning to make things easy for us.
• Nowadays Cloud computing, IoT and Social media generates lots of data, its
necessary to analyze data, process data and find useful information from data
to grow businesses or to find solutions to the problem and here machine
learning comes in picture.
• Following are some key points which show the importance of Machine
Learning:
• Rapid increment in the production of data
• Solving complex problems, which are difficult for a human
• Decision making in various sector including finance
• Finding hidden patterns and extracting useful information from data.
 How does Machine Learning work
• A Machine Learning system learns from historical data, builds the prediction
models, and whenever it receives new data, predicts the output for it.
• We can train machine learning algorithms by providing them huge amount of data
and then machine learn from data, construct the models, and predict the required
output automatically.
• The accuracy of predicted output depends upon the amount of data, as the huge
amount of data helps to build a better model which predicts the output more
accurately.
• Terms related to machine learning are :
• Algorithm: Algorithm defines logic behind machine learning model
• Model: A Model is trained by using machine learning algorithm
• Model takes input from machine learning algorithm and generates output.
• Training data: Machine learning model built (trained) using training data
• Testing data: Machine learning model evaluated(tested) using testing data
Machine Learning process
• Building predictive model that can be used to find solution for
problem statement.
• Steps of machine learning process:
• 1. Define objectives of problem:
• 2.Data gathering
• 3.Preparing data or Data cleaning
• 4.data Exploration
• 5.Building a model
• 6.Model evaluation and optimization
• 7.Prediction
• e.g. Weather forecast using machine learning.
 Types of Machine Learning
• At a broad level, machine learning can be classified into three types:
• Supervised learning
• Unsupervised learning
• Reinforcement learning
• 1) Supervised Learning
• Supervised learning is a type of machine learning method in which we provide
sample labeled data to the machine learning system in order to train it, and on
that basis, it predicts the output.
• The system creates a model using labeled data to understand the datasets and
learn about each data, once the training and processing are done then we test the
model by providing a sample data to check whether it is predicting the exact
output or not.
• The supervised learning is based on supervision, and it is the same as when a
student learns things in the supervision of the teacher.
• The example of supervised learning are classifying email as spam, labeling
webpages based on their content ,voice recognition,etc.
• Supervised learning can be grouped further in two categories of algorithms:
• Classification
• Regression
Types of Machine Learning
1) Supervised Learning
 Types of Machine Learning
• 2) Unsupervised Learning
• Unsupervised learning is a learning method in which a machine
learns without any supervision.
• The training is provided to the machine with the set of data that has
not been labeled, classified, or categorized, and the algorithm needs
to act on that data without any supervision.
• The goal of unsupervised learning is to classifies input data into
different clusters(groups) based on common features such as
size ,height, colour,etc.
• In unsupervised learning, we don't have a predetermined result. The
machine tries to find useful insights from the huge amount of data.
• It can be further classifieds into two categories of algorithms:
• Clustering
• Association
 Types of Machine Learning
• 2) Unsupervised Learning
 Types of Machine Learning
• 3) Reinforcement Learning
• Reinforcement learning is a feedback-based learning
method, in which a learning agent gets a reward for each right
action and gets a penalty for each wrong action.
• The agent learns automatically with these feedbacks and
improves its performance.
• The goal of an agent is to get the most reward points, and
hence, it improves its performance.
• The robotic dog, which automatically learns the movement of
his arms, is an example of Reinforcement learning.
• Not any input data given to machine ,machine learn itself
from environment.
• Reinforcement learning used in self driving cars and Google's
Alpha Go
 Types of Machine Learning
• 3) Reinforcement Learning
Comparison between different types of Machine Learning
 Neural Network and Deep Learning
• Neural Network: consist of computer program that mimic
the way human brain process information.
• Artificial Neural Network or Neural Network was modeled
after the human brain. Human has a mind to think and to
perform the task in a particular situation, but how can a
machine do that?
• For this purpose, an artificial brain was designed, which is
known as a Neural Network.
• As the human brain has neurons for passing information,
similarly neural network has nodes to perform that task. Nodes
are the mathematical functions.
 Neural Network and Deep Learning
• Deep learning is considered as evolution of machine learning
• Deep learning uses a programmable neural network that
enables machines to make accurate decisions without help
from human.
• Deep learning algorithms are created exactly just like machine
learning but it consists of many more levels of algorithms and
all these network of algorithms are together called as
artificial neural network that can learn from the data and
make intelligent decision on its own.
• Deep learning architectures have been applied to fields such
computer vision, speech recognition, audio recognition, social
network filtering, machine translation, drug design,
bioinformatics, medical image analysis, material inspection
and board game programs, where they have produced results in
some cases superior to and comparable to human experts.
Simple and Deep Learning Neural Network
Difference between Machine Learning and Deep Learning
 Difference between Machine Learning and Deep Learning
Machine Learning Deep Learning

1.Machine Learning is an evolution of 1. Deep Learning is an evolution of

artificial intelligence. machine Learning .

2.Machine Learning is a Superset of Deep 1.Deep Learning is a Subset of Machine

Learning. Learning

3.Machine Learning uses algorithms to 3.Deep learning structures algorithms in

parse data, learn from that data and make layer to create an artificial neural networks
informed decisions based on what it has that can learn from the data and make
learned. intelligent decisions on its own.
4. Data represented in machine learning is 4. Data represented in deep learning is
quite different as compared to deep quite different as compared to machine
learning as it uses structured data learning as it uses unstructured data
5. Machine Learning consists of 5.Deep Learning consists of Millions of
thousands of data points. data points. (i.e. Big Data)

6. Machine Learning algorithms required 6. Deep Learning algorithms required

lesser data sets for training. larger data sets for training.
7.Takes less time to train. 7.Takes longer time to train.