Intelligent System

6 th Semester

Compiled By: Er. Santosh Pandeya 1

Compiled By: Er. Santosh Pandeya 2
Related question:
•What is AI ? explain how AI can be used in real life.
•How machine intelligence is measured? Explain with
example.
•How day to day transaction of your office is managed by
using AI. Explain detail plan about it.(case study type).
•Explain the role of AI

Compiled By: Er. Santosh Pandeya 3

 INTRODUCTION
•Artificial + Intelligence
•Artificial means made by human
•Intelligence means
•The capacity to acquire and apply knowledge
•The faculty of thought and reason
•Superior powers of mind
•Ability to create ,reason, and understand

•Hence, AI is about the science and engineering necessary to create artifacts that can
•Acquire knowledge i.e. can learn and extract knowledge
•Reason with knowledge i.e. planning, explaining diagnosing etc.

• Artificial Intelligence is the part of computer science concerned with designing intelligence computer
systems, that is, systems that exhibit the characteristics that associate with intelligence in human
behavior

Compiled By: Er. Santosh Pandeya 4

 What is AI?
•The science and engineering of making intelligent machine
-John McCarthy.

•The art of creating machine that perform functions that require intelligence when
performed by people.
-Kurzwell, 1990
•AI is the study of how to make computers do things which at the moment , people do
better.
-E.Richand K.Knight.
• Artificial Intelligence is the part of computer science concerned with designing
intelligence computer systems, that is, systems that exhibit the characteristics that
associate with intelligence in human behavior
-Barr and Feigenbaum

Compiled By: Er. Santosh Pandeya 5

 4- dimension of AI
• The definition of AI can be divided into four dimension(approaches in AI)

• Acting humanly (Turing test approach)

• The test involves an interrogator who interacts with one human and one machine
• In artificial intelligence (AI), the Turing Test is a method for determining whether a computer is
capable of acting like a human or not

• Thinking Humanly: The Cognitive Modeling approach

• Cognitive modeling is an area of computer science that deals with simulating human problem

• Acting rationally
• Rational behavior means doing the right thing. The right thing is that which is expected to maximize
goal achievement
• given the available information. Rational Agent is one that acts so as to achieve the best outcome

• Thinking Rationally: The laws of thought approach

• Formal logic provides a precise notation for statements about things and their relationships
• Given sufficient memory and time, early computer programs were able to

Compiled By: Er. Santosh Pandeya 6

 Turing Test Approach

In artificial intelligence (AI), the Turing Test is a When we can count a

method for determining whether a computer is machine as being intelligent?
capable of acting like a human or not
-Turing test.
The test involves an interrogator who interacts with one
human and one machine
• According to this kind of test, a computer is deemed to
have artificial intelligence if it can mimic human
responses under specific conditions.
• In Turing's test, if the human being conducting the test is
unable to consistently determine whether an answer has
been given by a computer or by another human being,
then the computer is considered to have "passed" the
test
Compiled By: Er. Santosh Pandeya 7
 Thinking Humanly: The Cognitive Modeling approach

•e.g. : General Problem solver.

•Make the machines with mind. Cognition means the action or process of acquiring
knowledge and understanding through thought, experience and senses.

•Cognitive modeling is an area of computer science that deals with simulating

human problem solving and mental task processes in a computerized model.

•Such a model can be used to simulate or predict human behavior or performance

on tasks similar to the ones modeled.

•Cognitive modeling involves the design of computer simulation and mathematical

models of human cognition and perception

Compiled By: Er. Santosh Pandeya 8

 Acting rationally

•Rational behavior means doing the right thing. The right thing is that which is expected to maximize
goal achievement.

•Acting rationally means acting so as to achieve one's goals, given one's beliefs. An agent is just
something that perceives and acts.

•given the available information. Rational Agent is one that acts so as to achieve the best outcome.

•An intelligent agent is one that acts rationally with respect to its goals. For example, an agent that is
designed to play a game should make moves that increase its chances of winning the game.

Compiled By: Er. Santosh Pandeya 9

 Thinking Rationally: The laws of thought approach

•Formal logic provides a precise notation for statements about things and their
relationships.

•Given sufficient memory and time, early computer programs were able to solve
problems formulated in logical form, using automated reasoning and theorem proving
techniques.

1. today is Saturday
2. Saturday is holiday
Then we can conclude
Today is holiday.

Compiled By: Er. Santosh Pandeya 10

 Importance of AI
AI is becoming increasingly important in our world. Here are some reasons why:

Efficiency and Automation: AI can automate tasks that are repetitive, tedious, or dangerous for humans. This
can free up human workers to focus on more creative and strategic tasks.

Accuracy and Precision: AI can analyze vast amounts of data and identify patterns that humans might miss. This
can lead to more accurate predictions and better decision-making.

Innovation and Discovery: AI can be used to explore new ideas and possibilities. For example, AI can be used to
design new drugs, materials, and products.

Improved Quality of Life: AI has the potential to improve our quality of life in many ways, such as by providing
better healthcare, education, and transportation.

However, it's important to consider the ethical implications of AI as well, such as bias in algorithms and the
potential for job displacement.

Compiled By: Er. Santosh Pandeya 11

AI & Related Field

Compiled By: Er. Santosh Pandeya 12

Robotics: Robotics is the interdisciplinary study and practice of the design, construction, operation, and use of robots. The
Shadow robot hand system.

Machine learning: Machine Learning is the technique that gives computers the potential to learn without being programmed,
it is actively being used in daily life, machine learning application in daily life, even without knowing that. Fundamentally, it is
the science that enables machines to translate, execute and investigate data for solving real-world problems.

Neural Network
• The Neural Network is a field of artificial intelligence that makes use of Neurology ( a part of biology that concerns
the nerve and nervous system of the human brain). It incorporates cognitive science into machines to execute tasks.
The neural network mimics the human brain, which has an infinite number of neurons, and the neural network’s purpose
is to code brain-neurons into a system or computer.
• neural network is a set of algorithms that are used to identify elemental correlations among large amounts of data. In a
neural network,a neuron is a mathematical function (such as activation functions) whose job it is to gather and categories
data according to a certain structure. To perform tasks, the network heavily relies on statistical techniques such
as regression analysis.
• Neural Networks are widely used for fraud dete ction, risk analysis, stock-exchange prediction, sales prediction, and
many other purposes.
Natural Language Processing
NLP is a branch of computer science and artificial intelligence that allows computers and humans to communicate
using natural language. It’s a method of computational analysis of human languages. By mimicking human natural language,
it allows a machine to comprehend and interpret data.
Compiled By: Er. Santosh Pandeya 13
Deep Learning
• It is a process of learning in which the machine processes and analyses the input data using a number of ways until it
identifies a single acceptable output. It’s also referred to as self-learning of machines. To map the raw sequence of input
data to output, the machine uses a variety of random programs and algorithms.
• Deep learning would observe all possible human traits and behaviour databases, and it will undergo supervised
learning. This procedure includes:
 Detection of various human emotions and expressions.
 Identify humans and animals based on pictures, such as specific signs, markings, or traits.
 Recognize and memorise the voice of various speakers.
 Video and audio data conversion into text data.
 Identification of right and wrong gestures, classification of spam, and fraud activities (like fraud claims).

Cognitive Computing
• The objective of Cognitive Computing is to initiate and enhance human-machine interaction to accomplish complex
tasks and help in problem-solving.
• While working with humans on a variety of jobs, machines learn and comprehend human behaviour and feelings in a
variety of situations, and then recreate the human thought process in a computer model.
Computer Vision
• Computer vision is an important component of artificial intelligence because it enables the computer to identify, analyse,
and interpret visual input from real-world pictures and visuals by capturing and intercepting it.
• It uses deep learning and pattern recognition to extract visual information from any data, including images or video files
within PDF documents, Word documents, PowerPoint presentations, XL files, graphs, and photographs, among other
formats. Compiled By: Er. Santosh Pandeya 14
 Application of AI
• Artificial Intelligence has various applications in today's society.
• It is becoming essential for today's time because it can solve complex problems with an efficient way in multiple
industries, such as Healthcare, entertainment, finance, education, etc.
• AI is making our daily life more comfortable and fast.
Following are some sectors which have the application of Artificial Intelligence:

Compiled By: Er. Santosh Pandeya 15

• AI in Astronomy
• Artificial Intelligence can be very useful to solve complex universe problems. AI technology can be helpful for
understanding the universe such as how it works, origin, etc.
• AI in Healthcare
• In the last, five to ten years, AI becoming more advantageous for the healthcare industry and going to have a significant
impact on this industry.
• Healthcare Industries are applying AI to make a better and faster diagnosis than humans. AI can help doctors with
diagnoses and can inform when patients are worsening so that medical help can reach to the patient before
hospitalization.
• AI in Gaming
• AI can be used for gaming purpose. The AI machines can play strategic games like chess, where the machine needs to
think of a large number of possible places.
• AI in Finance
• AI and finance industries are the best matches for each other. The finance industry is implementing automation, chatbot,
adaptive intelligence, algorithm trading, and machine learning into financial processes.
• AI in Data Security
• The security of data is crucial for every company and cyber-attacks are growing very rapidly in the digital world. AI can be
used to make your data more safe and secure. Some examples such as AEG bot, AI2 Platforms, are used to determine
software bug and cyber-attacks in a better way.

Compiled By: Er. Santosh Pandeya 16

AI in Social Media
• Social Media sites such as Facebook, Twitter, and Snapchat contain billions of user profiles, which need to be stored and
managed in a very efficient way. AI can organize and manage massive amounts of data. AI can analyze lots of data to
identify the latest trends, hashtag, and requirement of different users.
AI in Travel & Transport
• AI is becoming highly demanding for travel industries. AI is capable of doing various travel related works such as from
making travel arrangement to suggesting the hotels, flights, and best routes to the customers. Travel industries are using
AI-powered chat bots which can make human-like interaction with customers for better and fast response.
AI in Automotive Industry
• Some Automotive industries are using AI to provide virtual assistant to their user for better performance. Such as Tesla
has introduced TeslaBot, an intelligent virtual assistant.
• Various Industries are currently working for developing self-driven cars which can make your journey more safe and
secure.
AI in Robotics:
• Artificial Intelligence has a remarkable role in Robotics. Usually, general robots are programmed such that they can
perform some repetitive task, but with the help of AI, we can create intelligent robots which can perform tasks with
their own experiences without pre-programmed.
• Humanoid Robots are best examples for AI in robotics, recently the intelligent Humanoid robot named as Erica and
Sophia has been developed which can talk and behave like humans.
AI in education:
AI in E-commerce
AI in Agriculture
AI in Entertainment Compiled By: Er. Santosh Pandeya 17
 Foundation of AI
The foundation of Artificial Intelligence (AI) can be understood through two main aspects:

The Conceptual Foundations: This refers to the historical ideas and philosophical underpinnings that led to
the development of AI as a field of study. It includes:
Early Thoughts: Since ancient times, humans have been fascinated by the idea of creating intelligent
machines. Myths and stories about artificial beings with human-like intelligence can be found in many
cultures.
Formalization of AI: The formal study of AI is generally considered to have begun in the 1950s. Alan Turing, a
pioneer in computer science, proposed the Turing Test as a way to determine if a machine could exhibit
intelligent behavior equivalent to a human. In 1956, John McCarthy and other researchers held a workshop
at Dartmouth College that is considered the founding event of AI as a field.

The Technical Foundations: This refers to the core technologies that make AI systems possible. These
include:
Machine Learning: This allows AI systems to learn from data without being explicitly programmed.
Natural Language Processing: This enables AI systems to understand and manipulate human language.
Computer Vision: This allows AI systems to interpret and analyze visual information.
Robotics: This field deals with the design, construction, operation, and application of robots.
Compiled By: Er. Santosh Pandeya 18
 History of AI

The history of artificial intelligence (AI) spans several decades and is characterized by significant milestones,
breakthroughs, and challenges. Here's a brief overview:

What happened after WWII?

• 1943: Warren McCulloch and Walter Pitts: a model of artificial boolean neurons to Perform computations.
• First steps toward connectionist computation and learning (Hebbian learning).
• Marvin Minsky and Dann Edmonds (1951) constructed the first neural network computer 1950: Alan
Turing's "Computing Machinery and Intelligence" — First complete vision of Al.

The birth of Al (1956)

• Dartmouth Workshop bringing together top minds on automata theory, neural nets and the study of
intelligence.
• Allen Newell and Herbert Simon: The logic theorist (first nonnumeric thinking program used for theorem
proving)
• For the next 20 years the field was dominated by these participants.

Compiled By: Er. Santosh Pandeya 19

Great expectations (1952-1969)
• Newell and Simon introduced the General Problem Solver.
• Imitation of human problem-solving
• Arthur Samuel (1952- ) investigated game playing (checkers) with great success.
• John McCarthy (1958- ):
• Inventor of Lisp (second-oldest high-level language)
• Logic oriented, Advice Taker (separation between knowledge and reasoning)
• Marvin Minsky (1958 - )
• Introduction of micro worlds that appear to require intelligence to solve: e.g. blocks-world. Anti-logic
orientation, society of the mind.

Collapse in Al research (1966 - 1973)

• Progress was slower than expected
• Unrealistic predictions
• Some systems lacked scalability. Combinatorial explosion in search.
• Fundamental limitations on techniques and representations.
• Minsky and Papert (1969) Perceptrons.

Compiled By: Er. Santosh Pandeya 20

Al revival through knowledge-based systems (1969-1970)
• General-purpose vs. domain specific
• E.g. the DENDRAL project (Buchanan et al. 1969) First successful knowledge intensive system.
• Expert systems
• MYCIN to diagnose blood infections (Feigenbaum et al.)
- Introduction of uncertainty in reasoning
• Increase in knowledge representation research
• Logic, frames, semantic nets

Al becomes an industry (1980 - present)

• RI at DEC (McDermott, 1982)
• Fifth generation project in Japan (1981)
• American response . . .
• Puts an end to the Al winter.
• Connectionist revival (1986 - present): (Return of Neural Network)
• Parallel distributed processing (RumelHart and McClelland, 1986); backprop.

Compiled By: Er. Santosh Pandeya 21

 Al becomes a science (1987 - present)
• In speech recognition: hidden markov models
• In neural networks
• In uncertain reasoning and expert systems: Bayesian network formalism

The emergence of intelligent agents (1995 - present)

The whole agent problem: "How does an agent act/behave embedded in real Environments with continuous
sensory inputs"

Compiled By: Er. Santosh Pandeya 22

 Knowledge

 Knowledge can be defined as the body of facts and principles accumulated by human kind or the act,
fact or state of knowing.
 Knowledge is "the sum of what is known: the body of truth, information, and principles acquired by
mankind." Or, "Knowledge is what I know, Information is what we know."
 Knowledge is "information combined with experience, context, interpretation, and reflection. It is a
high-value form of information that is ready to apply to decisions and actions." (T. Davenport et al.,
1998)
 It is having a familiarity with language, concepts, procedures, roles ideas, abstraction, places, facts and
associations with an ability to use these notions effectively in modeling different aspects of the world.
Without this ability, the facts and concepts are meaningless and therefore worthless. ' Knowledge
may be declarative or procedural.
Procedural
 It is also known as imperative knowledge.
 Procedural knowledge is a type of knowledge which is responsible for knowing how to do something.
 It can be directly applied to any task.
 It includes rules, strategies, procedures, agendas, etc.
 Procedural knowledge depends on the task on which it can be applied.
Compiled By: Er. Santosh Pandeya 23
Types of Knowledge

Compiled By: Er. Santosh Pandeya 24

 Procedural Knowledge
 It is also known as imperative knowledge.
 Procedural knowledge is a type of knowledge which is responsible for knowing how to do something.
 It can be directly applied to any task.
 It includes rules, strategies, procedures, agendas, etc.
 Procedural knowledge depends on the task on which it can be applied.

Declarative
 Declarative knowledge is to know about something.
 It includes concepts, facts, and objects.
 It is also called descriptive knowledge and expressed in declarativesentences.
 It is simpler than procedural language.
 Personal data in database is typical declarative knowledge.

Meta-knowledge:
 Knowledge about the other types of knowledge is called Meta-knowledge.

Compiled By: Er. Santosh Pandeya 25

 Heuristic knowledge
 A special type of knowledge used by human to solve complex problems.
 Heuristics are knowledge used to make good judgments or the strategies, tricks or "rules of thumb"
used to simplify the solution of a problem.
 Knowledge should not be composed with data. A physician treating a patient uses both knowledge
and data. The data is patient information like history, drug given etc whereas knowledge is what a
physician learned in medical school or in internship, specialization or practice.

 Structural knowledge:
 Structural knowledge is basic knowledge to problem-solving.
 It describes relationships between various concepts such as kind of, part of, and grouping of something.
 It describes the relationship that exists between concepts or objects.

Compiled By: Er. Santosh Pandeya 26

 The relation between knowledge and intelligence:
Knowledge of real-worlds plays a vital role in intelligence and same for creating artificial intelligence. Knowledge plays an
important role in demonstrating intelligent behavior in AI agents. An agent is only able to accurately act on some input
when he has some knowledge or experience about that input.

Let's suppose if you met some person who is speaking in a language which you don't know, then how you will able to act
on that. The same thing applies to the intelligent behavior of the agents.

As we can see in below diagram, there is one decision maker which act by sensing the environment and using knowledge.
But if the knowledge part will not present then, it cannot display intelligent behavior.

Compiled By: Er. Santosh Pandeya 27

 Importance of Knowledge
 Al has provided new meaning and importance to knowledge.
 It is now possible to package specialized knowledge and sell it with a system that can
use it to reason and draw conclusions.
 Imagine being able to purchase a reliable advisor that gives high level of professional
advice in specialized areas such as manufacturing techniques, sound financial strategies,
ways to improve one's health and many more important matters.

Compiled By: Er. Santosh Pandeya 28

 Knowledge Representation (KR)

 KR is the theory and practice of representing knowledge (facts about the world) into computer systems (or agents) and
this representation needs to be in the form such that the agents can store, manipulate and develop new knowledge
(inference) from the existing.
 A subarea of Artificial Intelligence concerned with understanding, designing, and implementing ways of representing
information in computers so that programs (agents) can use this information
 to derive information that is implied by it,
 to converse with people in natural languages,
 to decide what to do next
 to plan future activities,
 to solve problems in areas that normally require human expertise.

Framework of Knowledge Representation

• Computer requires a well-defined problem description to process and provide well-defined acceptable solution.
• To collect fragments of knowledge we need first to formulate a description in our spoken language and then represent it
in formal language so that computer can understand. The computer can then use an algorithm to compute an answer.
• This process is illustrated below.

Compiled By: Er. Santosh Pandeya 29

The steps are :
 The informal formalism of the problem takes place first.
 It is then represented formally and the computer produces an output.
 This output can then be represented in a informally described solution that user understands or checks for
consistency

Fig. Knowledge Representation Framework

Compiled By: Er. Santosh Pandeya 30

 What is an Agent?

 An agent can be anything that perceiveits environment through sensors and act upon that environment
through actuators. An Agent runs in the cycle of perceiving, thinking, and acting.
An agent can be:

Human-Agent: A human agent has eyes, ears, and other organs which work for sensors and hand, legs, vocal
tract work for actuators.
Robotic Agent: A robotic agent can have cameras, infrared range finder, NLP for sensors and various motors
for actuators.
Software Agent: Software agent can have keystrokes, file contents as sensory input and act on those inputs
and display output on the screen.
Hence the world around us is full of agents such as thermostat, cellphone, camera, and even we are also
agents.
Sensor: Sensor is a device which detects the change in the environment and sends the information to other
electronic devices. An agent observes its environment through sensors.
Actuators: Actuators are the component of machines that converts energy into motion. The actuators are only
responsible for moving and controlling a system. An actuator can be an electric motor, gears, rails, etc.
Effectors: Effectors are the devices which affect the environment. Effectors can be legs, wheels, arms, fingers,
wings, fins, and display screen.
Compiled By: Er. Santosh Pandeya 31
 Learning/machine learning:

•Machine learning is an application of artificial intelligence (AI) that focused on building applications that
learn from data and improve their accuracy over time without being programmed. These application can
access data and use it to learn for themselves

•"Changes in the system that are adaptive in the sense that they enable the system to do the same task or
tasks drawn from the same population more efficiently the next time.“

•From a conceptual standpoint, learning is a process that improves the knowledge of an AI program by making
observations about its environment.

•From a technical/mathematical standpoint, AI learning processes focused on processing a collection ofinput-

output pairs for a specific functionand predicts the outputs for new inputs.

Compiled By: Er. Santosh Pandeya 32

 Steps of Machine Learning:

How machine learning works

•Select and prepare a training data set
•Choose an algorithm to run on the training
data set
•Training the algorithm to create the model
•Using and improving the model

Compiled By: Er. Santosh Pandeya 33

1 -Data Collection
•The quantity & quality of your data dictate how accurate our model is
•The outcome of this step is generally a representation of data which we will use for
training
•Using pre-collected data, by way of datasets from Kaggle, UCI, etc., still fits into this step

2 -Data Preparation
•Wrangle data and prepare it for training
•Clean that which may require it (remove duplicates, correct errors, deal with missing
values, normalization, data type conversions, etc.)
•Randomize data, which erases the effects of the particular order in which we collected
and/or otherwise prepared our data
•Visualize data to help detect relevant relationships between variables or class
imbalances (bias alert!), or perform other exploratory analysis
•Split into training and evaluation sets

Compiled By: Er. Santosh Pandeya 34

3 -Choose a Model
•Different algorithms are for different tasks; choose the right one

4 -Train the Model

•The goal of training is to answer a question or make a prediction correctly as often as
possible
•Linear regression example: algorithm would need to learn values form(orW) andb(xis
input,yis output)
•Each iteration of process is a training step

5 -Evaluate the Model

•Uses some metric or combination of metrics to "measure" objective performance of
model
•Test the model against previously unseen data
•This unseen data is meant to be somewhat representative of model performance in
the real world, but still helps tune the model (as opposed to test data, which does not)
Compiled By: Er. Santosh Pandeya 35
6 -Parameter Tuning
•This step refers tohyperparametertuning, which is an "artform" as opposed to a science
•Tune model parameters for improved performance
•Simple model hyper parameters may include: number of training steps, learning rate,
initialization values and distribution, etc.

7 -Make Predictions
•Using further (test set) data which have, until this point, been withheld from the model
(and for which class labels are known), are used to test the model; a better
approximation of how the model will perform in the real world

Compiled By: Er. Santosh Pandeya 36

 Types of learning

•AI Learning Models: Knowledge-Based Classification

•Inductive Learning
•Deductive Learning

•Feedback-Based Classification
•Unsupervised Learning
•Supervised Learning
• Semi-supervised Learning
•Reinforcement Learning

Compiled By: Er. Santosh Pandeya 37

 Inductive learning
•Inductive learning is a kind of learning in which, given a set of examples an agent tries to
estimate or create an evaluation function.
•Inductive learning, also known as discovery learning, is a process where the learner
discovers rules by observing examples.
•Most inductive learning is supervised learning, in which examples provided with
classifications.
•This type of AI learning model is based on inferring a general rule from datasets of input-
output pairs.
•Used to identify if there is a pattern; to see if things regularly happen in the same way.
•A model or hypothesis is made about the problem using the training data, and it is
believed to hold over new unseen data later when the model is used.
•induction is a bottom-up type of reasoning that uses available data as evidence for an
outcome

Compiled By: Er. Santosh Pandeya 38

 Deductive learning
•This type of AI learning technique starts with the series of rules and infers
new rules that are more efficient in the context of a specific AI algorithm.
•Deductive learning is a teacher-centered approach to education. Under this,
the learners are first given rules in the form of lectures
•Deduction is the reverse of induction. If induction is going from the specific to
the general, deduction is going from the general to the specific.
•Example:
•Explanation-Based Learning(EBL) and Relevance-Based Learning(RBL)
•EBL extracts general rules from examples by “generalizing” the explanation.
•RBL focuses on identifying attributes and deductive generalizations from
simple example

Compiled By: Er. Santosh Pandeya 39

Supervised learning
•The machine has a “teacher” who guides it by providing sample inputs along with the desired
output. The machine then maps the inputs and the outputs.
•Supervised learning models use external feedback to learning functions that map inputs to output
observations. In those models the external environment acts as a “teacher” of the AI algorithms.
•Supervised learning algorithms try to model relationships and dependencies between the target
prediction output and the input features such that we can predict the output values for new data
based on those relationships which it learned from the previous data sets.

Unsupervised learning:
•The computer is trained with unlabeled data.
•Here there’s no teacher at all, actually the computer might be able to teach you new things after it
learns patterns in data, these algorithms a particularly useful in cases where the human expert
doesn’t know what to look for in the data.
•are the family of machine learning algorithms which are mainly used inpattern detection and
descriptive modeling.
•These algorithms try to use techniques on the input data tomine for rules,detect patterns, and
summarize and group the data pointswhich help in deriving meaningful insights and describe the
data better to the users. Compiled By: Er. Santosh Pandeya 40
Semi-supervised learning
•In the previous two types, either there are no labels for all the observation in the dataset or labels
are present for all the observations. Semi-supervised learning falls in between these two
•These methods exploit the idea that even though the group memberships of the unlabeled data
are unknown, this data carries important information about the group parameters.
•Semi-supervised learning is supervised learning where the training data contains very few labeled
examples and a large number of unlabeled examples.

Reinforcement learning
•This method aims at using observations gathered from the interaction with the environment to
take actions that would maximize the reward or minimize the risk.
•Reinforcement learning algorithm (called the agent) continuously learns from the environment in
an iterative fashion. In the process, the agent learns from its experiences of the environment until it
explores the full range of possible states.
•It allows machines and software agents to automatically determine the ideal behavior within a
specific context, in order to maximize its performance.
•Simple reward feedback is required for the agent to learn its behavior; this is known as the
reinforcement signal.
Compiled By: Er. Santosh Pandeya 41
 Assignment-1
1. Discuss the difference between Machine Learning, Semi-Supervised and Deep Learning with examples.
2. Define AI. What is the difference between “ Strong AI” and “Weak AI”? What are some Misconceptions
about AI? Make clear with explanation.
3. Explain about automated reasoning in AI.

- Must be submitted within 7 days

Compiled By: Er. Santosh Pandeya 42

Thank You !

Compiled By: Er. Santosh Pandeya 43