UNIT – I

Overview of A.I: Introduction to AI, Importance of AI, AI and its related field, AI
techniques, Criteria for success.
Problems, problem space and search: Defining the problem as a state space search,
Production system and its characteristics, Issues in the design of the search problem
Heuristic search techniques : Generate and test, hill climbing, best first search technique,
problem reduction, constraint satisfaction

What is Artificial Intelligence (AI)?

In today's world, technology is growing very fast, and we are getting in touch with different
new technologies day by day.

Here, one of the booming technologies of computer science is Artificial Intelligence which is
ready to create a new revolution in the world by making intelligent machines. The Artificial
Intelligence is now all around us. It is currently working with a variety of subfields, ranging
from general to specific, such as self-driving cars, playing chess, proving theorems, playing
music, Painting, etc.

AI is one of the fascinating and universal fields of Computer science which has a great scope
in future. AI holds a tendency to cause a machine to work as a human.

Artificial Intelligence is composed of two words Artificial and Intelligence, where Artificial
defines "man-made," and intelligence defines "thinking power", hence AI means "a man-
made thinking power."

So, we can define AI as:

It is a branch of computer science by which we can create intelligent machines which

can behave like a human, think like humans, and able to make decisions.
Artificial Intelligence exists when a machine can have human based skills such as learning,
reasoning, and solving problems

With Artificial Intelligence you do not need to preprogram a machine to do some work,
despite that you can create a machine with programmed algorithms which can work with own
intelligence, and that is the awesomeness of AI.

It is believed that AI is not a new technology, and some people says that as per Greek myth,
there were Mechanical men in early days which can work and behave like humans.

Why Artificial Intelligence?

Before Learning about Artificial Intelligence, we should know that what is the importance of
AI and why should we learn it. Following are some main reasons to learn about AI:
 o With the help of AI, you can create such software or devices which can solve real-
world problems very easily and with accuracy such as health issues, marketing, traffic
issues, etc.
o With the help of AI, you can create your personal virtual Assistant, such as Cortana,
Google Assistant, Siri, etc.
o With the help of AI, you can build such Robots which can work in an environment
where survival of humans can be at risk.
o AI opens a path for other new technologies, new devices, and new Opportunities.

Goals of Artificial Intelligence

Following are the main goals of Artificial Intelligence:

1. Replicate human intelligence

2. Solve Knowledge-intensive tasks
3. An intelligent connection of perception and action
4. Building a machine which can perform tasks that requires human intelligence such as:
o Proving a theorem
o Playing chess
o Plan some surgical operation
o Driving a car in traffic
5. Creating some system which can exhibit intelligent behavior, learn new things by
itself, demonstrate, explain, and can advise to its user.

Uses of Artificial Intelligence

Important uses of Artificial Intelligence are given below:

1. In Medical Science

o Artificial Intelligence has made an unprecedented impact in the medical industry and
hence changed the face of the medical industry. Various machine learning algorithms
and models have efficiently predicted various important use cases, such as
determining whether a particular patient has malignant or benign cancer or tumor
based on symptoms, health records, and history. It is also being used in future
predictions where patients are well informed about their deteriorating health and what
they should do to return to a normal and healthy life.
o Artificial intelligence has created a virtual care private assistant specifically built for
people's needs. It is widely used to monitor, research different types of cases, and
analyze past cases and their outcomes. It also seeks to improve their model's and
assistants' efficiency by predicting what could be improved and making themselves
smarter.
o The use of healthcare bots is another efficient move taken by the medical industry to
work their way up in medicine, which is known to provide 24/7 assistance and take up
the less important work of managing appointments. It has not have been possible
without the intervention of these smart artificial intelligence-based machines.
2. In the Field of Air Transport
 o One of the major systematic transport in the world is air transport, and there has
become an urgent need to optimize their mode of operation. Here came the
involvement of Artificial Intelligence, where the machine is involved in planning the
routes along with the flight landing and take-off charts.
o Artificial intelligence has been used in many aircraft, navigation maps, taxing routes,
and a quick examination of the entire cockpit panel to ensure the correct operation of
each component. Hence, it gives very promising results and is being adopted very
frequently. The ultimate aim of artificial intelligence in air transport is to give easier
and more comfortable travel to human beings.
3. In the field of banking and financial institutions

o Artificial Intelligence plays a vital role in managing financial transactions and

handling many other activities in the bank. The day-to-day operations of banks, such
as transactions and financial operations, stock market money and their management,
etc., are being handled more easily and efficiently by these machine learning models.
o Use cases such as anti-money laundering where suspicious financial transactions are
being monitored and reported to regulators are a classic example of artificial
intelligence in the banking and financial industry. Other use cases include credit
systems analysis which is popular among credit card companies. Suspicious credit
card transactions are tracked geographically and acted upon and resolved based on
various parameters.
4. In the field of gaming and entertainment

o From virtual reality games to today's modern games, this is one industry where
artificial intelligence has made the biggest leap forward. Bots are always there for you
to play with, so you don't need another person to play.
o The level of personalized detail and graphics is also possible due to the advent of
Artificial Intelligence and is taking this industry to a different level.
5. AI Achieves Unprecedented Accuracy

o AI achieves remarkable accuracy through deep neural networks, which was

previously impossible.
o For example, Google Search and your interactions with Alexa are all deep learning-
based, becoming more accurate the more we use them. AI techniques are also used in
medical fields to search for cancer cells on MRI with high precision as highly trained
radiologists.
6. AI Is Reliable & Quick

AI performs computer-generated tasks consistently, extensively, and reliably. However,

human skills are required to set up the system and ask the appropriate questions.

7. AI Adds Intelligence to Products

o AI will not be sold as an individual product. Instead, your products will be enhanced
with AI integration, like the Apple products discussed with the Siri feature.
o Chatbots, automation, and smart devices, combined with massive amounts of data,
can improve many technologies at home and in the workplace.
8. AI Evaluates Deep Data
 o With big data and computing power, it has become possible to develop fraud
detection systems that were nearly impossible just a few years ago.
o It would help if you had a lot of data to train deep learning models because they learn
directly from the data. The more data, the more accurate they are.
9. AI Fully Utilized Data

It would help if you implemented AI to get answers from the data. The role of data is more
important than ever; Its gives you an edge over your competitors if you have the best data
system in this competitive industry because the best data will win!

What is an AI Technique?
Artificial Intelligence (AI) refers to developing computer systems for performing tasks
requiring human intelligence. These systems assess large amounts of data to identify patterns
and make logical decisions based on the collected information. The ultimate goal of AI is to
create machines to carry out diverse tasks.

Artificial Intelligence techniques refer to a set of methods and algorithms used to develop
intelligent systems that can perform tasks requiring human-like intelligence. Some of the
widely used ones are:
 Machine Learning.
 Natural Language Processing.
 Computer Vision.
 Deep Learning
 Data Mining
 Robotics.

Natural Language Processing(NLP)

One of the most important and fast-developing approaches in the sphere of artificial
intelligence is Natural Language Processing, focused on how computers and human
language interact. NLP closes the gap between digital data processing and human
communication by giving machines the ability to understand, interpret, and generate
human languages in a meaningful and practical way. Probably one of the most exciting
and significant fields of AI research and application is a cross-disciplinary discipline
combining linguistics, computer science, and artificial intelligence in an attempt to solve
the intricacies of human language.

Basically, NLP deals with some major activities such as language translation,
production, and understanding. It draws support from many subfields like phonetics,
concerned with the sounds; pragmatics, concerned with the meaning in context;
semantics, concerned with meaning; and syntax, concerned with the structure of the
language. NLP combines these elements to construct systems that can recognize
voices, translate machines, conduct sentiment analysis, and chatbots in a
comprehensive manner.

NLP encompasses a range of techniques for interpreting, understanding, and generating

human language that are:

o Language Understanding: This has to do with how well robots can

understand the structure and semantics of human language. Methods like
dependency parsing, named entity recognition, and part-of-speech tagging aid
in dissecting and examining sentences to comprehend their grammatical
structure and word connections. For example, in sentiment analysis, natural
language processing algorithms may discern, from word and context analysis,
whether a text represents positive, negative, or neutral feelings.
o Language Generation:This alludes to robots' capacity to generate prose that
resembles that of humans. Text generation-where the system can compose
articles, tales, or even code depending on inputs-and text summarization-
where the system generates succinct summaries of lengthy documents-are
two techniques in this field. Recent developments in this area, such as the
creation of massive language models like GPT-3, have greatly enhanced the
coherence and quality of machine-generated text, making it more challenging
to tell it apart from human writing.
o Language Translation: Translating text or voice across languages is the aim
of machine translation, which is one of the most useful uses of natural
language processing. Large dictionaries and rule-based systems played a
major role in early machine translation techniques. However, by learning from
enormous volumes of bilingual text data, neural machine translation systems
like Google Translate have grown significantly more accurate and fluent with
the development of neural networks and deep learning.

Computer Vision(CV)
Within the field of artificial intelligence, computer vision is a potent and quickly
developing technique that focuses on enabling machines to comprehend and make
judgments based on visual data. This multidisciplinary area combines concepts from
electrical engineering, neurology, and computer science to imitate the human visual
system and enable computers to comprehend digital pictures and movies to a high
degree. Applications for CV are many and range from basic tasks like handwritten digit
recognition to sophisticated systems like autonomous driving.

Some of the various methods in computer vision are:

 o Classification of Image: Sorting a picture into one of many specified classes
is the goal of image classification, which is a basic problem in computer
vision. In this procedure, a picture is fed into a machine learning model that
has been trained on a sizable dataset of labeled images, such as a
Convolutional Neural Network (CNN). In order to assign a label, the model
takes characteristics out of the picture, such as edges, textures, and forms.
Image classification is used in face identification, medical diagnosis, and
product sorting in warehouses.
o Identification of Object: Object detection goes beyond simple categorization
to include both the identification of things in a picture and the specific position
of those objects. In object detection, methods like Single Shot MultiBox
Detector (SSD), You Only Look Once (YOLO), and Region-based CNN (R-
CNN) are frequently employed. These models are appropriate for real-time
video analysis, driverless cars, and surveillance since they can process
pictures in real time.
o Segmenting Image: Compared to object identification, image segmentation
is a more detailed operation since it entails dividing a picture into several
segments or areas, each of which represents a distinct object or component
of an item. Semantic segmentation, which assigns a category to every pixel,
and instance segmentation, which distinguishes between several objects
belonging to the same class, are the two primary categories of picture
segmentation. Image segmentation is essential for autonomous driving since
it aids in comprehending road situations and is used in medical imaging to
detect and evaluate anatomical features.

Machine Learning(ML)
A fundamental component of artificial intelligence, machine learning enables computers
to learn from data, spot patterns, and make choices with the least amount of human
input. By using statistical techniques, machine learning algorithms allow robots to gain
experience and become more proficient at activities. This method is different from
traditional programming, which codes specific instructions for each and every eventuality
that might arise. Rather, machine learning models are highly effective in dynamic and
complicated contexts because they learn from examples and adapt to new
circumstances.

ML is broadly categorized into supervised learning, unsupervised learning, and

reinforcement learning.

o Supervised Learning: Supervised learning involves training models using

labeled data, where each input sample yields the proper output. This method
is comparable to classroom instruction. Classification methods like Support
Vector Machines (SVM) and Decision Trees, which divide inputs into discrete
groups, and Linear Regression, which predicts a continuous output, are
common algorithms. Applications include sentiment analysis, spam
identification, and medical diagnosis frequently making use of supervised
learning.
o Unsupervised Learning: In unsupervised learning, models are trained on
unlabeled data, enabling the system to find underlying structures or hidden
 patterns. While Dimensionality Reduction techniques like Principal
Component Analysis (PCA) reduce the number of variables in a dataset,
clustering algorithms like K-means and hierarchical clustering group
comparable data points together. Applications include anomaly detection,
exploratory data analysis, and consumer segmentation.
o Reinforcement Learning(RL): Reinforcement learning (RL), which takes its
cues from behavioral psychology, teaches agents to make decisions by
rewarding good behavior and penalizing bad behavior. As it engages with its
surroundings, the agent gains knowledge on how to optimize repeated gains.
RL makes use of methods such as Policy Gradient Methods and Q-learning.
Notable uses for it include robotics, autonomous driving, and gameplay (like
AlphaGo), where systems need to learn the best strategies over time.

Deep Learning(DL)
A key method in artificial intelligence, deep learning is a subset of machine learning (ML)
that focuses on modeling and solving complicated problems with artificial neural
networks. Deep learning models can learn from vast amounts of data and make
judgments by mimicking the functions of the human brain. These models have
transformed artificial intelligence and made major strides possible in a number of areas,
including speech recognition, computer vision, natural language processing, and more.
Core concepts of deep learning are:

o ANN: The artificial neural network serves as the fundamental building block of
deep learning models. An artificial neural network (ANN) is made up of layers
of networked nodes, or neurons, where each node is a mathematical process.
An ANN's main layer types are input layers, which are responsible for
accepting data, hidden layers, which analyze data, and output layers, which
generate the final prediction. To reduce prediction error, a weight is assigned
to each link between nodes during training.
o DNN: Deep neural networks (ANNs) are ANNs with more than one hidden
layer. DNNs are able to learn hierarchical representations of data, capturing
complex patterns and relationships, thanks to the network's depth, or the
number of layers. This capacity is necessary to solve increasingly complicated
problems that are beyond the scope of simpler models.
o CNN: CNNs are designed specifically to handle structured grid data, including
picture data. They make use of fully linked, pooling, and convolutional layers.
In order to extract features from the input data, convolutional layers apply
filters; pooling layers then lower the dimensionality of these features; and fully
connected layers then interpret the features for tasks involving classification
or regression. The fields of object identification, image synthesis, and image
recognition have all advanced greatly because of CNNs.
o RNN: RNNs are intended for time-series analysis and sequential data. Their
architecture has loops that enable information to remain constant over time
steps. The vanishing gradient issue is resolved by variations like Gated
Recurrent Units (GRU) and Long Short-Term Memory (LSTM), which allow
the model to capture long-term dependence. Speech recognition, time-series
forecasting, and natural language processing (NLP) are three common
applications for RNNs.