100% found this document useful (1 vote)
208 views42 pages

Seminar Report

This document is a seminar report submitted by Shreya Singh for the degree of Bachelor of Technology in Computer Science and Engineering. It discusses artificial intelligence and deep learning. The report includes an introduction to AI, its history, types of AI such as weak AI and general AI, what comprises AI, goals of AI like problem solving and natural language processing, categories of AI including conventional AI and computational intelligence, fields where AI is applied such as automation and robotics, and pros and cons of AI. It also contains figures, acknowledgments and references.

Uploaded by

sammuel john
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
100% found this document useful (1 vote)
208 views42 pages

Seminar Report

This document is a seminar report submitted by Shreya Singh for the degree of Bachelor of Technology in Computer Science and Engineering. It discusses artificial intelligence and deep learning. The report includes an introduction to AI, its history, types of AI such as weak AI and general AI, what comprises AI, goals of AI like problem solving and natural language processing, categories of AI including conventional AI and computational intelligence, fields where AI is applied such as automation and robotics, and pros and cons of AI. It also contains figures, acknowledgments and references.

Uploaded by

sammuel john
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 42

A

Seminar Report
on
“ARTIFICIAL INTELLIGENCE AND DEEP
LEARNING”
submitted
in partial fulfillment
for the award of the Degree of
Bachelor of Technology
in
Department of Computer Science & Engineering

Seminar Coordinator: Submitted by:


Mr.Harpreet Singh Gill Shreya Singh
Associate Professor 17ESKCS753

Department of Computer Science & Engineering


Swami Keshvanand Institute of Technology, M & G, Jaipur
Rajasthan Technical University,Kota
Session 2019-2020

Swami Keshvanand Institute of Technology,


Management & Gramothan, Jaipur
Department of Computer Science and Engineering

CERTIFICATE

This is to certify that Ms Shreya Singh Parihar, a student of B.Tech(Computer Sci-

ence & Engineering)VII semester has submitted her Seminar Report entitled ”Arti-
ficial Intelligence And Deep Learning” under my guidance.

Name-Mr.Harpreet Singh Gill

Associate Professor

Department of Computer Science & Engineering, SKIT, Jaipur i


Acknowledgement

It is my pleasure to be indebted to various people, who directly or indirectly con-


tributed in the development of this work and who influenced my thinking, behavior,
and acts during the course of study.

I express my sincere gratitude to Dr. Mukesh Kumar Gupta, HOD,(Department)


for providing me an opportunity to work in a consistent direction and providing all
necessary means to complete my presentations and report thereafter.

I would like to thank my esteemed supervisor Mr. Harpreet Singh Gill,Department


of Computer Science & Engineering ,Swami Keshvanand Institute of Technology,
Management and Gramothan ,Jaipur for his valuable suggestion,keen interest,constant
encouragement,incessant inspiration and continuous help throughout this work. His
excellent guidance has been instrumental in making this work a success.

I express my sincere heartfelt gratitude to all the staff members of Department of


Computer Science & Engineering who helped me directly or indirectly during this
course of work.

I would also like to express my thanks to my parents for their support and bless-
ings. A special thank goes to all my friends for their support in completion of this
work.

NAME-Shreya Singh Parihar


ROLL No.-17ESKCS753

Department of Computer Science & Engineering, SKIT, Jaipur ii


List of Figures

1.1 Artificial Intelligence . . . . . . . . . . . . . . . . . . . . . . . . 3

3.1 Applications of Deep Learning . . . . . . . . . . . . . . . . . . . 6

4.1 Applications of Artificial Intelligence . . . . . . . . . . . . . . . 10

9.1 Applications of Artificial Intelligence . . . . . . . . . . . . . . . 22

10.1 Artificial Intelligence . . . . . . . . . . . . . . . . . . . . . . . . 24

11.1 Example of Deep Learning . . . . . . . . . . . . . . . . . . . . . 26

13.1 Applications of Deep Learning . . . . . . . . . . . . . . . . . . . 31

Department of Computer Science & Engineering,SKIT, Jaipur iii


Contents

1 INTRODUCTION-ARTIFICIAL INTELLIGENCE 2
1.1 Artificial . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2
1.2 Intelligence . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2
1.3 Artificial Intlligence . . . . . . . . . . . . . . . . . . . . . . . . . . 2

2 HISTORY 4
2.1 History Of A.I. . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4
2.1.1 1950s: The Beginnings of Artificial Intelligence (AI) Research 4
2.1.2 1960:- . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5
2.1.3 1980:- . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5
2.1.4 1990 :- . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5

3 TYPES OF A.I. 6
3.1 Weak AI or Narrow AI: . . . . . . . . . . . . . . . . . . . . . . . . 6
3.2 General AI: . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7
3.3 Super AI: . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7
3.4 Reactive Machines . . . . . . . . . . . . . . . . . . . . . . . . . . 8
3.5 Limited Memory . . . . . . . . . . . . . . . . . . . . . . . . . . . 8
3.6 Theory of Mind . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8
3.7 Self-Awareness . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9

4 WHAT COMPRISES TO A.I. 10

5 GOALS OF A.I. 11
5.1 Deduction, reasoning, problem solving:- . . . . . . . . . . . . . . . 11
5.2 Knowledge representation:- . . . . . . . . . . . . . . . . . . . . . 11
5.3 Planning:- . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 12
5.4 Natural language processing:- . . . . . . . . . . . . . . . . . . . . 12
5.5 Motion and manipulation:- . . . . . . . . . . . . . . . . . . . . . . 12
5.6 . Perception:- . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 13

Department of Computer Science & Engineering,SKIT, Jaipur iv


5.7 Social intelligence:- . . . . . . . . . . . . . . . . . . . . . . . . . . 13
5.8 General intelligence:- . . . . . . . . . . . . . . . . . . . . . . . . . 13

6 CATEGORIES OF A.I. 14
6.1 Conventional AI :- . . . . . . . . . . . . . . . . . . . . . . . . . . 14
6.1.1 Methods include: . . . . . . . . . . . . . . . . . . . . . . 14
6.2 Computational Intelligence (CI) . . . . . . . . . . . . . . . . . . . 14
6.2.1 Methods include: . . . . . . . . . . . . . . . . . . . . . . . 15

7 Fields in which AI methods are implemented 16


7.1 Automation:- . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 16
7.2 Cybernetics:- . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 16
7.3 Hybrid intelligent system :- . . . . . . . . . . . . . . . . . . . . . . 16
7.4 Intelligent agent:- . . . . . . . . . . . . . . . . . . . . . . . . . . . 17
7.5 Intelligent control:- . . . . . . . . . . . . . . . . . . . . . . . . . . 17
7.6 Automated reasoning:- . . . . . . . . . . . . . . . . . . . . . . . . 17
7.7 Data mining:- . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 17
7.8 Behavior-based robotics:- . . . . . . . . . . . . . . . . . . . . . . . 18
7.9 Developmental robotics:- . . . . . . . . . . . . . . . . . . . . . . . 18
7.10 Evolutionary robotics:- . . . . . . . . . . . . . . . . . . . . . . . . 18
7.11 Chatbot:- . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 18
7.12 Knowledge Representation:- . . . . . . . . . . . . . . . . . . . . . 18

8 PROS AND CONS OF A.I. 19


8.1 ADVANTAGES . . . . . . . . . . . . . . . . . . . . . . . . . . . . 19
8.2 DISADVANTAGES . . . . . . . . . . . . . . . . . . . . . . . . . . 19

9 APPLICATIONS OF A.I 20
9.1 Hospitals and medicine . . . . . . . . . . . . . . . . . . . . . . . . 20
9.2 Heavy industry . . . . . . . . . . . . . . . . . . . . . . . . . . . . 20
9.3 Game Playing . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 21
9.4 Speech Recognition . . . . . . . . . . . . . . . . . . . . . . . . . . 21
9.5 Understanding Natural Language . . . . . . . . . . . . . . . . . . . 21
9.6 Computer Vision . . . . . . . . . . . . . . . . . . . . . . . . . . . 21
9.7 Expert Systems . . . . . . . . . . . . . . . . . . . . . . . . . . . . 22
9.8 Heuristic Classification . . . . . . . . . . . . . . . . . . . . . . . . 22

10 FUTURE OF A.I. 23

Department of Computer Science & Engineering, SKIT, Jaipur v


11 DEEP LEARNING 25
11.1 INTRODUCTION . . . . . . . . . . . . . . . . . . . . . . . . . . 25
11.2 Example of Deep Learning . . . . . . . . . . . . . . . . . . . . . . 26

12 ARCHITECTURES 27
12.1 Deep Neural Networks . . . . . . . . . . . . . . . . . . . . . . . . 27
12.2 Deep Belief Networks . . . . . . . . . . . . . . . . . . . . . . . . . 27
12.3 Recurrent Neural Networks . . . . . . . . . . . . . . . . . . . . . . 27

13 DEEP LEARNING APPLICATIONS 28


13.1 Self Driving Cars . . . . . . . . . . . . . . . . . . . . . . . . . . . 28
13.2 News Aggregation and Fraud News Detection . . . . . . . . . . . . 28
13.3 Natural Language Processing . . . . . . . . . . . . . . . . . . . . . 28
13.4 Virtual Assistants . . . . . . . . . . . . . . . . . . . . . . . . . . . 28
13.5 Entertainment . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 28
13.6 Visual Recognition . . . . . . . . . . . . . . . . . . . . . . . . . . 29
13.7 Fraud Detection . . . . . . . . . . . . . . . . . . . . . . . . . . . . 29
13.8 Healthcare . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 29
13.9 Personalisations . . . . . . . . . . . . . . . . . . . . . . . . . . . . 29
13.10Colourisation of Black and White images . . . . . . . . . . . . . . 29
13.11Adding sounds to silent movies . . . . . . . . . . . . . . . . . . . . 29
13.12Automatic Machine Translation . . . . . . . . . . . . . . . . . . . 29
13.13Automatic Handwriting Generation . . . . . . . . . . . . . . . . . 30
13.14Automatic Game Playing . . . . . . . . . . . . . . . . . . . . . . . 30
13.15Language Translations . . . . . . . . . . . . . . . . . . . . . . . . 30
13.16Pixel Restoration . . . . . . . . . . . . . . . . . . . . . . . . . . . 30
13.17Photo Descriptions . . . . . . . . . . . . . . . . . . . . . . . . . . 30
13.18Voice Controlled Assistance . . . . . . . . . . . . . . . . . . . . . 31
13.19Automatic Image Caption Generation . . . . . . . . . . . . . . . . 31
13.20. Detecting Developmental Delay in Children . . . . . . . . . . . . 31

14 PROS AND CONS OF DEEP LEARNING 32


14.1 ADVANTAGES . . . . . . . . . . . . . . . . . . . . . . . . . . . . 32
14.2 DISADVANTAGES . . . . . . . . . . . . . . . . . . . . . . . . . . 32

15 FUTURE OF DEEP LEARNING 33

Department of Computer Science & Engineering, SKIT, Jaipur vi


16 CONCLUSION 34
16.1 Deep Learning . . . . . . . . . . . . . . . . . . . . . . . . . . . . 34
16.2 Artificial Intelligence . . . . . . . . . . . . . . . . . . . . . . . . . 34

17 REFRENCES 35

Department of Computer Science & Engineering, SKIT, Jaipur vii


Chapter 1

INTRODUCTION-ARTIFICIAL
INTELLIGENCE

1.1 Artificial
The simple definition of artificial is that objects that are made or produced by
human beings rather than occurring naturally.

1.2 Intelligence
The simple definition of intelligence is a process of entail a set of skills of problem
solving, enabling to resolve genuine problems or difficulties that encounters and to
create an effective product and must also entail the potential for finding or creating
problems and thereby laying the groundwork for the acquisition of new knowledge

1.3 Artificial Intlligence


Artificial intelligence is a branch of science which deals with helping machines
find solution to complex problems in a more human like fashion. This generally
involves borrowing characteristics from human intelligence, and applying them as
algorithms in a computer friendly way. A more or less or flexible or efficient ap-
proach can be taken depending on the requirements established, which influences
how artificial intelligent behavior appears. Artificial intelligence is generally asso-
ciated with computer science, but it has many important links with other fields such
as maths, psychology, cognition , biology and philosophy , among many others .
Our ability to combine knowledge from all these fields will ultimately benefits our
progress in the quest of creating an intelligent artificial being. A.I is mainly con-
cerned with the popular mind with the robotics development, but also the main field

Department of Computer Science & Engineering,SKIT, Jaipur 1


of practical application has been as an embedded component in the areas of soft-
ware development which require computational understandings and modeling such
as such as finance and economics, data mining and physical science. A.I in the fields
of robotics is the make a computational models of human thought processes. It is
not enough to make a program that seems to behave the way human do. You want
to make a program that does it the way humans do it. In computer science they also
the problems bcoz we have to make a computer that are satisfy for understanding the
high-level languages and that was taken to be A.I.

Figure 1.1: Artificial Intelligence

Department of Computer Science & Engineering, SKIT, Jaipur 2


Chapter 2

HISTORY

2.1 History Of A.I.


The intellectual roots of AI, and the concept of intelligent machines, may be found
in Greek mythology. Intelligent artifacts appear in literature since then, with real me-
chanical devices actually demonstrating behaviour with some degree of intelligence.
After modern computers became available following World War-II, it has become
possible to create programs that perform difficult intellectual tasks.

2.1.1 1950s: The Beginnings of Artificial Intelligence (AI) Research


With the development of the electronic computer in 1941 and the stored program
computer in 1949 the condition for research in artificial intelligence is given, still
the observation of a link between human intelligence and machines was not widely
observed until the late in 1950 The first working AI programs were written in 1951
to run on the Ferranti Mark I machine of the University of Manchester (UK): a
draughts-playing program written by Christopher Strachey and a chess-playing pro-
gram written by Dietrich Prinz. The person who finally coined the term artificial
intelligence and is regarded as the father of the of AL is John McCarthy. In 1956
he organized a conference “the Darthmouth summer research project on artificial
intelligence” to draw the talent and expertise of others interested in machine intelli-
gence of a month of brainstorming. In the following years AI research centers began
forming at the Carnegie Mellon University as well as the Massachusetts Institute
of Technology (MIT) and new challenges were faced: 1) The creation of systems
that could efficiently solve problems by limiting the search. 2) The construction of
systems that could learn by themselves.

Department of Computer Science & Engineering,SKIT, Jaipur 3


2.1.2 1960:-
By the middle of the 1960s, research in the U.S. was heavily funded by the De-
partment of Defense and laboratories had been established around the world. AI’s
founders were profoundly optimistic about the future of the new field: Herbert Si-
mon predicted that ”machines will be capable, within twenty years, of doing any
work a man can do” and Marvin Minsky agreed, writing that ”within a generation
. By the 1960’s, America and its federal government starting pushing more for the
development of AI. The Department of Defense started backing several programs
in order to stay ahead of Soviet technology. The U.S. also started to commercially
market the sale of robotics to various manufacturers. The rise of expert systems also
became popular due to the creation of Edward Feigenbaum and Robert K. Lindsay’s
DENDRAL. DENDRAL had the ability to map the complex structures of organic
chemicals, but like many AI inventions, it began to tangle its results once the pro-
gram had too many factors built into it... the problem of creating ’artificial intelli-
gence’ will substantially be solved”. The same predicament fell upon the program
SHRDLU which would use robotics through a computer so the user could ask ques-
tions and give commands in English.

2.1.3 1980:-
In the early 1980s, AI research was revived by the commercial success of expert
systems, a form of AI program that simulated the knowledge and analytical skills of
one or more human experts. By 1985 the market for AI had reached over a billion
dollars. At the same time, Japan’s fifth generation computer project inspired the U.S
and British governments to restore funding for academic research in the field. In the
1990s and early 21st century, AI achieved its greatest successes, albeit somewhat
behind the scenes. Artificial intelligence is used for logistics, data mining, medical
diagnosis and many other areas throughout the technology industry

2.1.4 1990 :-
From 1990s until the turn of the century, AI has reached some incredible land-
marks with the creation of intelligent agents. Intelligent agents basically use their
surrounding environment to solve problems in the most efficient and effective man-
ner. In 1997, the first computer (named Deep Blue) beat a world chess champion.
In 1995, the VaMP car drove an entire 158 km racing track without any help from
human intelligence. In 1999, humanoid robots began to gain popularity as well as
the ability to walk around freely.

Department of Computer Science & Engineering, SKIT, Jaipur 4


Chapter 3

TYPES OF A.I.

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. Following is flow diagram which explain the types of AI.

Figure 3.1: Applications of Deep Learning

AI type-1: Based on Capabilities

3.1 Weak AI or Narrow AI:


Narrow AI is a type of AI which is able to perform a dedicated task with intel-
ligence.The most common and currently available AI is Narrow AI in the world of
Artificial Intelligence.

Department of Computer Science & Engineering,SKIT, Jaipur 5


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.

Apple Siriis a good example of Narrow AI, but it operates with a limited pre-
defined range of functions.

IBM’s Watson supercomputer also comes under Narrow AI, as it uses an Expert
system approach combined with Machine learning and natural language processing.

Some Examples of Narrow AI are playing chess, purchasing suggestions on e-


commerce site, self-driving cars, speech recognition, and image recognition.

3.2 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.

3.3 Super AI:


Super AI is a level of Intelligence of Systems at which machines could surpass hu-
man intelligence, and can perform any task better than human with cognitive prop-
erties. 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.

Department of Computer Science & Engineering, SKIT, Jaipur 6


Super AI is still a hypothetical concept of Artificial Intelligence. Development of
such systems in real is still world changing task.

Artificial Intelligence type-2: Based on functionality

3.4 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.

3.5 Limited Memory


Limited memory machines can store past experiences or some data for a short
period of time.

These machines can use stored data for a limited time period only.

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.

3.6 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.

Department of Computer Science & Engineering, SKIT, Jaipur 7


3.7 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.

Department of Computer Science & Engineering, SKIT, Jaipur 8


Chapter 4

WHAT COMPRISES TO A.I.

Artificial Intelligence is not just a part of computer science even it’s so vast and
requires lots of other factors which can contribute to it.

To create the AI first we should know that how intelligence is composed, so the
Intelligence is an intangible part of our brain which is a combination of Reasoning,
learning, problem-solving perception, language understanding, etc.
To achieve the above factors for a machine or software Artificial Intelligence
requires the following discipline:

Mathematics Biology Psychology Sociology Computer Science Neurons Study


Statistics

Figure 4.1: Applications of Artificial Intelligence

Department of Computer Science & Engineering,SKIT, Jaipur 9


Chapter 5

GOALS OF A.I.

The general problem of simulating (or creating) intelligence has been broken down
into a number of specific sub-problems. These consist of particular traits or capabil-
ities that researchers would like an intelligent system to display. The traits described
below have received the most attention.

5.1 Deduction, reasoning, problem solving:-


For difficult problems, most of these algorithms can require enormous computa-
tional resources most experience a ”combinatorial explosion”: the amount of mem-
ory or computer time required becomes astronomical when the problem goes be-
yond a certain size. The search for more efficient problem-solving algorithms is a
high priority for AI research. Human beings solve most of their problems using fast,
intuitive judgements rather than the conscious, step-by-step deduction that early AI
research was able to model. AI has made some progress at imitating this kind of
”sub-symbolic” problem solving: embodied agent approaches emphasize the impor-
tance of sensorimotor skills to higher reasoning; neural net research attempts to sim-
ulate the structures inside the brain that give rise to this skill; statistical approaches
to AI mimic the probabilistic nature of the human ability to guess.

5.2 Knowledge representation:-


Knowledge representation and knowledge engineering are central to AI research.
Many of the problems machines are expected to solve will require extensive knowl-
edge about the world. Among the things that AI needs to represent are: objects,
properties, categories and relations between objects; situations, events, states and
time; causes and effects; knowledge about knowledge (what we know about what

Department of Computer Science & Engineering,SKIT, Jaipur 10


other people know) and many other, less well researched domains. A representation
of ”what exists” is an ontology: the set of objects, relations, concepts and so on
that the machine knows about. The most general are called upper ontologies, which
attempt provide a foundation for all other knowledge

5.3 Planning:-
Intelligent agents must be able to set goals and achieve them. They need a way to
visualize the future and be able to make choices that maximize the utility (or ”value”)
of the available choices. In classical planning problems, the agent can assume that it
is the only thing acting on the world and it can be certain what the consequences of
its actions may be. However, if the agent is not the only actor, it must periodically
ascertain whether the world matches its predictions and it must change its plan as
this becomes necessary, requiring the agent to reason under uncertainty.

5.4 Natural language processing:-


Natural language processing gives machines the ability to read and understand the
languages that humans speak. A sufficiently powerful natural language processing
system would enable natural language user interfaces and the acquisition of knowl-
edge directly from humanwritten sources, such as Internet texts. Some straightfor-
ward applications of natural language processing include information retrieval (or
text mining) and machine translation. A common method of processing and ex-
tracting meaning from natural language is through semantic indexing. Increases in
processing speeds and the drop in the cost of data storage makes indexing large
volumes of abstractions of the users input much more efficient.

5.5 Motion and manipulation:-


The field of robotics is closely related to AI. Intelligence is required for robots
to be able to handle such tasks as object manipulation and navigation, with sub-
problems of localization (knowing where you are, or finding out where other things
are), mapping (learning what is around you, building a map of the environment),
and motion planning (figuring out how to get there) or path planning (going from
one point in space to another point, which may involve compliant motion - where
the robot moves while maintaining physical contact with an object).

Department of Computer Science & Engineering, SKIT, Jaipur 11


5.6 . Perception:-
Machine perceptionis the ability to use input from sensors (such as cameras, mi-
crophones, sonar and others more exotic) to deduce aspects of the world. Computer
vision is the ability to analyze visual input. A few selected subproblems are speech
recognition facial recognition and object recognition.

5.7 Social intelligence:-


Affective computing is the study and development of systems and devices that
can recognize, interpret, process, and simulate human affects. It is an interdisci-
plinary field spanning computer sciences, psychology, and cognitive science While
the origins of the field may be traced as far back as to early philosophical inquiries
into emotion. A motivation for the research is the ability to simulate empathy. The
machine should interpret the emotional state of humans and adapt its behaviour to
them, giving an appropriate response for those emotions. Emotion and social skills
play two roles for an intelligent agent. First, it must be able to predict the actions
of others, by understanding their motives and emotional states. Also, in an effort to
facilitate human-computer interaction, an intelligent machine might want to be able
to display emotions—even if it does not actually experience them itself—in order to
appear sensitive to the emotional dynamics of human interaction.

5.8 General intelligence:-


Most researchers think that their work will eventually be incorporated into a ma-
chine with general intelligence (known as strong AI), combining all the skills above
and exceeding human abilities at most or all of them. A few believe that anthropo-
morphic features like artificial consciousness or an artificial brain may be required
for such a project. Many of the problems above may require general intelligence to
be considered solved. For example, even a straightforward, specific task like ma-
chine translation requires that the machine read and write in both languages (NLP),
follow the author’s argument (reason), know what is being talked about (knowledge),
and faithfully reproduce the author’s intention (social intelligence). A problem like
machine translation is considered ”AI-complete”. In order to solve this particular
problem, you must solve all the problems.

Department of Computer Science & Engineering, SKIT, Jaipur 12


Chapter 6

CATEGORIES OF A.I.

AI divides roughly into two schools of thought: 1. Conventional AI. 2. Computa-


tional Intelligence (CI).

6.1 Conventional AI :-
Conventional AI mostly involves methods now classified as machine learning, characterized by
formalism and statistical analysis. This is also known as symbolic AI, logical AI, neat AI and
Good Old Fashioned Artificial Intelligence (GOFAI).

6.1.1 Methods include:


1. Expert systems: apply reasoning capabilities to reach a conclusion. An expert
system can process large amounts of known information and provide conclusions
based on them.

2. Case based reasoning

3. Bayesian networks

4. Behavior based AI: a modular method of building AI systems by hand.

6.2 Computational Intelligence (CI)


Computational Intelligence involves iterative development or learning (e.g. pa-
rameter tuning e.g. in connectionist systems). Learning is based on empirical data
and is associated with non-symbolic AI, scruffy AI and soft computing.

Department of Computer Science & Engineering,SKIT, Jaipur 13


6.2.1 Methods include:
1. Neural networks: systems with very strong pattern recognition capabilities.

2. Fuzzy systems: techniques for reasoning under uncertainty, has been widely
used in modern industrial and consumer product control systems.

3. Evolutionary computation: applies biologically inspired concepts such as pop-


ulations, mutation and survival of the fittest to generate increasingly better solutions
to the problem. These methods most notably divide into evolutionary algorithms
(e.g. genetic algorithms) and swarm intelligence (e.g. ant algorithms).

Department of Computer Science & Engineering, SKIT, Jaipur 14


Chapter 7

Fields in which AI methods are implemented

7.1 Automation:-
Automation is the use of machines, control systems and information technologies
to optimize productivity in the production of goods and delivery of services. The
correct incentive for applying automation is to increase productivity, and/or quality
beyond that possible with current human labor levels so as to realize economies
of scale, and/or realize predictable quality levels. automation greatly decreases the
need for human sensory and mental requirements while increasing load capacity,
speed, and repeatability.

7.2 Cybernetics:-
Cybernetics in some ways is like the science of organisation, with special empha-
sis on the dynamic nature of the system being organised. The human brain is just
such a complex organisation which qualifies for cybernetic study. It has all the char-
acteristics of feedback, storage, etc. and is also typical of many large businesses or
Government departments. Cybernetics is that of artificial intelligence, where the
aim is to show how artificially manufactured systems can demonstrate intelligent
behaviour.

7.3 Hybrid intelligent system :-


Hybridization of different intelligent systems is an innovative approach to con-
struct computationally intelligent systems consisting of artificial neural network,
fuzzy inference systems, rough set, approximate reasoning and derivative free opti-
mization methods such as evolutionary computation, swarm intelligence, bacterial

Department of Computer Science & Engineering,SKIT, Jaipur 15


foraging and so on. The integration of different learning and adaptation techniques,
to overcome individual limitations and achieve synergetic effects through hybridiza-
tion or fusion of these techniques, has in recent years contributed to a emergence of
large number of new superior class of intelligence known as Hybrid Intelligence.

7.4 Intelligent agent:-


In artificial intelligence, an intelligent agent (IA) is an autonomous entity which
observes through sensors and acts upon an environment using actuators (i.e. it is an
agent) and directs its activity towards achieving goals.

7.5 Intelligent control:-


Intelligent Control or self-organising/learning control is a new emerging discipline
that is designed to deal with problems. Rather than being model based, it is expe-
riential based. Intelligent Control is the amalgam of the disciplines of Artificial
Intelligence, Systems Theory and Operations Research. It uses most recent experi-
ences or evidence to improve its performance through a variety of learning schemas,
that for practical implementation must demonstrate rapid learning convergence, be
temporally stable, be robust to parameter changes and internal and external distur-
bances.

7.6 Automated reasoning:-


The study of automated reasoning helps produce software that allows computers
to reason completely, or nearly completely, automatically. Although automated rea-
soning is considered a sub-field of artificial intelligence, it also has connections with
theoretical computer science, and even philosophy.

7.7 Data mining:-


Data mining (the analysis step of the ”Knowledge Discovery in Databases” pro-
cess, or KDD), an interdisciplinary subfield of computer science, is the computa-
tional process of discovering patterns in large data sets involving methods at the
intersection of artificial intelligence, machine learning, statistics, and database sys-
tems. The overall goal of the data mining process is to extract information from a
data set and transform it into an understandable structure for further use

Department of Computer Science & Engineering, SKIT, Jaipur 16


7.8 Behavior-based robotics:-
Behavior-based robotics is a branch of robotics that bridges artificial intelligence
(AI), engineering and cognitive science. Its dual goals are: (1) To develop methods
for con- trolling artificial systems, ranging from physical robots to simulated ones
and other autonomous software agents (2) To use robotics to model and understand
biological sys- tems more fully, typically, animals ranging from insects to humans.
Cognitive robotics.

7.9 Developmental robotics:-


Developmental Robotics (DevRob), sometimes called epigenetic robotics, is a
methodology that uses metaphors from neural development and developmental psy-
chology to develop the mind for autonomous robots. The program that simulates the
functions of genome to develop a robot’s mental capabilities is called a developmen-
tal program.

7.10 Evolutionary robotics:-


Evolutionary robotics (ER) is a methodology that uses evolutionary computation
to develop controllers for autonomous robots

7.11 Chatbot:-
Chatterbot, a chatter robot is a type of conversational agent, a computer program
designed to simulate an intelligent conversation with one or more human users via
auditory or textual methods. Internet Relay Chat bot, a set of scripts or an indepen-
dent program that connects to Internet Relay Chat as a client, and so appears to other
IRC users as another user.

7.12 Knowledge Representation:-


Knowledge representation (KR) is an area of artificial intelligence research aimed
at representing knowledge in symbols to facilitate inferencing from those knowledge
elements, creating new elements of knowledge. The KR can be made to be indepen-
dent of the underlying knowledge model or knowledge base system (KBS) such as
a semantic network

Department of Computer Science & Engineering, SKIT, Jaipur 17


Chapter 8

PROS AND CONS OF A.I.

8.1 ADVANTAGES
AI drives down the time taken to perform a task. It enables multi-tasking and eases
the workload for existing resources.

AI enables the execution of hitherto complex tasks without significant cost outlays.

AI operates 24x7 without interruption or breaks and has no downtime

AI augments the capabilities of differently abled individuals

AI has mass market potential, it can be deployed across industries.

AI facilitates decision-making by making the process faster and smarter.

8.2 DISADVANTAGES
High cost of implementation.

Can’t replace humans.

Doesn’t improve with experience

Lacks creativity.

Risk of unemployement.

Department of Computer Science & Engineering,SKIT, Jaipur 18


Chapter 9

APPLICATIONS OF A.I

9.1 Hospitals and medicine


A medical clinic can use artificial intelligence systems to organize bed schedules,
make a staff rotation, and provide medical information. Artificial neural networks
are used as clinical decision support systems for medical diagnosis, such as in Con-
cept Processing technology in EMR software.

Other tasks in medicine that can potentially be performed by artificial intelligence


include

1) Computer-aided interpretation of medical images. Such systems help scan digi-


tal images, e.g. from computed tomography, for typical appearances and to highlight
conspicuous sections, such as possible diseases. A typical application is the detec-
tion of a tumor.

2) Heart sound analysis.

9.2 Heavy industry


Robots have become common in many industries. They are often given jobs that
are considered dangerous to humans. Robots have proven effective in jobs that are
very repetitive which may lead to mistakes or accidents due to a lapse in concentra-
tion and other jobs which humans may find degrading.

Department of Computer Science & Engineering,SKIT, Jaipur 19


9.3 Game Playing
1) This prospered greatly with the Digital Revolution, and helped introduce peo-
ple, especially children, to a life of dealing with various types of Artificial Intelli-
gence

2) You can also buy machines that can play master level chess for a few hundred
dollars. There is some AI in them, but they play well against people mainly through
brute force computation–looking at hundreds of thousands of positions.

3) The internet is the best example were one can buy machine and play various
games

9.4 Speech Recognition


In the 1990s, computer speech recognition reached a practical level for limited
purposes. Thus United Airlines has replaced its keyboard tree for flight information
by a system using speech recognition of flight numbers and city names. It is quite
convenient. On the other hand, while it is possible to instruct some computers using
speech, most users have gone back to the keyboard and the mouse as still more
convenient.

9.5 Understanding Natural Language


Just getting a sequence of words into a computer is not enough. Parsing sentences
is not enough either. The computer has to be provided with an understanding of the
domain the text is about, and this is presently possible only for very limited domains.

9.6 Computer Vision


The world is composed of three-dimensional objects, but the inputs to the human
eye and computer’s TV cameras are two dimensional. Some useful programs can
work solely in two dimensions, but full computer vision requires partial threedimen-
sional information that is not just a set of two-dimensional views. At present there
are only limited ways of representing three-dimensional information directly, and
they are not as good as what humans evidently use.

Department of Computer Science & Engineering, SKIT, Jaipur 20


9.7 Expert Systems
A “knowledge engineer” interviews experts in a certain domain and tries to em-
body their knowledge in a computer program for carrying out some task. How well
this works depends on whether the intellectual mechanisms required for the task
are within the present state of AI. One of the first expert systems was MYCIN in
1974, which diagnosed bacterial infections of the blood and suggested treatments. It
did better than medical students or practicing doctors, provided its limitations were
observed.

9.8 Heuristic Classification


One of the most feasible kinds of expert system given the present knowledge of AI
is to put some information in one of a fixed set of categories using several sources
of information. An example is advising whether to accept a proposed credit card
purchase. Information is available about the owner of the credit card, his record
of payment and also about the item he is buying and about the establishment from
which he is buying it (e.g., about whether there have been previous credit card frauds
at this establishment).

Figure 9.1: Applications of Artificial Intelligence

Department of Computer Science & Engineering, SKIT, Jaipur 21


Chapter 10

FUTURE OF A.I.

1. In the next 10 years technologies in narrow fields such as speech recognition


will continue to improve and will reach human levels.

2. In 10 years AI will be able to communicate with humans in unstructured English


using text or voice, navigate (not perfectly) in an unprepared environment and will
have some rudimentary common sense (and domain-specific intelligence).

3. We will recreate some parts of the human (animal) brain in silicon. The fea-
sibility of this is demonstrated by tentative hippocampus experiments in rats There
are two major projects aiming for human brain simulation, CCortex and IBM Blue
Brain.

4. There will be an increasing number of practical applications based on digi-


tally recreated aspects human intelligence, such as cognition, perception, rehearsal
learning, or learning by repetitive practice.

5. The development of meaningful artificial intelligence will require that machines


acquire some variant of human consciousness.

6. Systems that do not possess self-awareness and sentience will at best always be
very brittle.

7. Without these uniquely human characteristics, truely useful and powerful as-
sistants will remain a goal to achieve. To be sure, advances in hardware, storage,
parallel processing architectures will enable ever greater leaps in functionality

Department of Computer Science & Engineering,SKIT, Jaipur 22


8. Systems that are able to demonstrate conclusively that they possess self aware-
ness, language skills, surface, shallow and deep knowledge about the world around
them and their role within it will be needed going forward.

9. However the field of artificial consciousness remains in its infancy.

10. The early years of the 21st century should see dramatic strides forward in this
area however

Figure 10.1: Artificial Intelligence

Department of Computer Science & Engineering, SKIT, Jaipur 23


Chapter 11

DEEP LEARNING

11.1 INTRODUCTION
Deep learning is based on the branch of machine learning, which is a subset of
artificial intelligence. Since neural networks imitate the human brain and so deep
learning will do. In deep learning, nothing is programmed explicitly. Basically, it
is a machine learning class that makes use of numerous nonlinear processing units
so as to perform feature extraction as well as transformation. The output from each
preceding layer is taken as input by each one of the successive layers.

Deep learning models are capable enough to focus on the accurate features them-
selves by requiring a little guidance from the programmer and are very helpful in
solving out the problem of dimensionality. Deep learning algorithms are used, espe-
cially when we have a huge no of inputs and outputs.

Since deep learning has been evolved by the machine learning, which itself is a
subset of artificial intelligence and as the idea behind the artificial intelligence is
to mimic the human behavior, so same is ”the idea of deep learning to build such
algorithm that can mimic the brain”.

Deep learning is implemented with the help of Neural Networks, and the idea
behind the motivation of Neural Network is the biological neurons, which is nothing
but a brain cell.

Deep learning is a collection of statistical techniques of machine learning for learn-


ing feature hierarchies that are actually based on artificial neural networks.

Department of Computer Science & Engineering,SKIT, Jaipur 24


So basically, deep learning is implemented by the help of deep networks, which
are nothing but neural networks with multiple hidden layers.

11.2 Example of Deep Learning


In the example given above, we provide the raw data of images to the first layer
of the input layer. After then, these input layer will determine the patterns of local
contrast that means it will differentiate on the basis of colors, luminosity, etc. Then
the 1st hidden layer will determine the face feature, i.e., it will fixate on eyes, nose,
and lips, etc. And then, it will fixate those face features on the correct face template.
So, in the 2nd hidden layer, it will actually determine the correct face here as it can
be seen in the above image, after which it will be sent to the output layer. Likewise,
more hidden layers can be added to solve more complex problems, for example, if
you want to find out a particular kind of face having large or light complexions. So,
as and when the hidden layers increase, we are able to solve complex problems.

Figure 11.1: Example of Deep Learning

Department of Computer Science & Engineering, SKIT, Jaipur 25


Chapter 12

ARCHITECTURES

12.1 Deep Neural Networks


It is a neural network that incorporates the complexity of a certain level, which
means several numbers of hidden layers are encompassed in between the input and
output layers. They are highly proficient on model and process non-linear associa-
tions.

12.2 Deep Belief Networks


A deep belief network is a class of Deep Neural Network that comprises of multi-
layer belief networks. Steps to perform DBN: With the help of the Contrastive Di-
vergence algorithm, a layer of features is learned from perceptible units. Next, the
formerly trained features are treated as visible units, which perform learning of fea-
tures. Lastly, when the learning of the final hidden layer is accomplished, then the
whole DBN is trained.

12.3 Recurrent Neural Networks


It permits parallel as well as sequential computation, and it is exactly similar to
that of the human brain (large feedback network of connected neurons). Since they
are capable enough to reminisce all of the imperative things related to the input they
have received, so they are more precise.

Department of Computer Science & Engineering,SKIT, Jaipur 26


Chapter 13

DEEP LEARNING APPLICATIONS

13.1 Self Driving Cars


Deep Learning is the force that is bringing autonomous driving to life. A million
sets of data are fed to a system to build a model, to train the machines to learn, and
then test the results in a safe environment.

13.2 News Aggregation and Fraud News Detection


Extensive use of deep learning in news aggregation is bolstering efforts to cus-
tomize news as per readers.

13.3 Natural Language Processing


Natural Language Processing through Deep Learning is trying to achieve the same
thing by training machines to catch linguistic nuances and frame appropriate re-
sponses.

13.4 Virtual Assistants


Virtual assistants use deep learning to know more about their subjects ranging
from your dine-out preferences to your most visited spots or your favorite songs.

13.5 Entertainment
Content editing and auto-content creation are now a reality thanks to Deep Learn-
ing and its contribution to face and pattern recognition

Department of Computer Science & Engineering,SKIT, Jaipur 27


13.6 Visual Recognition
Visual recognition through deep neural networks is boosting growth in this seg-
ment of digital media management by using convolutional neural networks, Tensor-
flow, and Python extensively.

13.7 Fraud Detection


Fraud prevention and detection are done based on identifying patterns in customer
transactions and credit scores, identifying anomalous behavior and outliers.

13.8 Healthcare
Healthcare giants are mitigating health risks associated with readmissions while
bringing down the costs.

13.9 Personalisations
Deep Learning is empowering efforts of e-commerce giants like Amazon, E-Bay,
Alibaba, etc. to provide seamless personalized experiences in the form of product
recommendations, personalized packages and discounts, and identifying large rev-
enue opportunities around the festive season

13.10 Colourisation of Black and White images


Deep Learning Technology today, it is now applied to objects and their context
within the photograph – in order to colour the image, just as human operator’s ap-
proach.

13.11 Adding sounds to silent movies


This task is done using training 1000 videos – that have drum sticks sound striking
on different surfaces and creating different sounds.

13.12 Automatic Machine Translation


Automatic machine translation has been around for a long time, but deep learning
is achieving top results in two specific areas:

Department of Computer Science & Engineering, SKIT, Jaipur 28


1) Automatic Translation of Text.

2) Automatic Translation of Images

13.13 Automatic Handwriting Generation


his application of Deep Learning involves the generation of new set of handwrit-
ings for a given corpus of a word or phrase.

13.14 Automatic Game Playing


Here, a corpus of text is learnt, and new text is generated, word-by-word or character-
by-character. This model of Deep Learning is capable of learning how to spell,
punctuate and even capture the style of the text in the corpus sentences

13.15 Language Translations


With the Google Translate app, it is now possible to automatically translate pho-
tographic images with text into a real-time language of your choice.

13.16 Pixel Restoration


Deep Learning network to take very low resolution images of faces and predict
the person’s face through it. This method was known as the Pixel Recursive Super
Resolution.

13.17 Photo Descriptions


The computer not only learnt how to classify the elements in the photograph, but
also managed to describe them with English grammar. Demographic and Election
Predictions

It was seen that the model was capable of predicting the demographics of each
area, just via the car makeup. Deep Dreaming

This technique, as the name suggests, allows the computer to hallucinate on top of
an existing photo – thereby generating a reassembled dream.

Department of Computer Science & Engineering, SKIT, Jaipur 29


13.18 Voice Controlled Assistance
When we talk about voice control assistance, then Siri is the one thing that comes
into our mind. So, you can tell Siri whatever you want it to do it for you, and it will
search it for you and display it for you.

13.19 Automatic Image Caption Generation


Whatever image that you upload, the algorithm will work in such a way that it
will generate caption accordingly. If you say blue colored eye, it will display a
blue-colored eye with a caption at the bottom of the image.

13.20 . Detecting Developmental Delay in Children


Speech disorders, autism, and developmental disorders can deny a good quality
of life to children suffering from any of these problems. An early diagnosis and
treatment can have a wonderful effect on the physical, mental, and emotional health
of differently-abled children.

Figure 13.1: Applications of Deep Learning

Department of Computer Science & Engineering, SKIT, Jaipur 30


Chapter 14

PROS AND CONS OF DEEP LEARNING

14.1 ADVANTAGES
It lessens the need for feature engineering.

It eradicates all those costs that are needless

It easily identifies difficult defects.

It results in the best-in-class performance on problems.

14.2 DISADVANTAGES
It requires an ample amount of data.

It is quite expensive to train.

It does not have strong theoretical groundwork.

It only learns through the observations

It comprises of biases issues.

Department of Computer Science & Engineering,SKIT, Jaipur 31


Chapter 15

FUTURE OF DEEP LEARNING

Current growth of DL research and industry applications demonstrate its “ubiqui-


tous” presence in every facet of AI — be it NLP or computer vision applications.
With time and research opportunities, unsupervised learning methods may deliver
models that will closely mimic human behavior. The apparent conflict between con-
sumer data protection laws and research needs of high volumes of consumer data
will continue.

Deep learning technology’s limitations in being able to “reason” is a hindrance


to automated, decision-support tools. Google’s acquisition of DeepMind Technolo-
gies holds promise for global marketers. The future ML and DL technologies must
demonstrate learning from limited training materials, and transfer learning between
contexts, continuous learning, and adaptive capabilities to remain useful. Though
globally popular, deep learning may not be the only savior of AI solutions.

If deep learning technology research progresses in the current pace, developers


may soon find themselves outpaced and will be forced to take intensive training.
Deep learning networks will demystify computer memory. Neural architecture search
will play a key role in building datasets for DL models.
NAS will continue to use reinforcement learning to search convolutional archi-
tectures.

Department of Computer Science & Engineering,SKIT, Jaipur 32


Chapter 16

CONCLUSION

16.1 Deep Learning


Deep learning can be a time and cost efficient way to determine malignancy asso-
ciated changes. It can provide doctors a quicker evaluation of what types of cells a
pap-smear test contains. More extensive studies are needed.

16.2 Artificial Intelligence


Artificial Intelligence and Machine Learning are products of both science and
myth. The idea that machines could think and perform tasks just as humans do is
thousands of years old. The cognitive truths expressed in AI and Machine Learning
systems are not new either.

AI is at the centre of a new enterprise to build computational models of intel-


ligence. The main assumption is that intelligence (human or otherwise) can be
represented in terms of symbol structures and symbolic operations which can be
programmed in a digital computer. AI programs can outperform human experts.
Now the great challenge of AI is to find ways of representing the commonsense
knowledge and experience that enable people to carry out everyday activities such
as holding a wide-ranging conversation, or finding their way along a busy street.

Department of Computer Science & Engineering,SKIT, Jaipur 33


Chapter 17

REFRENCES

[1] www.sas.com

[2] javatpoint.com/artificial intelligence

[3] www.investopedia.com

[4] javatpoint.com/deeplearning

[5] en.wikipidea.org

Department of Computer Science & Engineering,SKIT, Jaipur 34

You might also like